© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9070
    Prev
    Next
    INDEX
    Explanations

    past tense verbs describing actions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron spots decimal‐formatted numeric tokens (numbers with a fractional part).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    past tense verbs describing actions or events that occurred.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    past-tense action verbs, often in phrasal verb constructions, signaling completed events in narrative text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    0.74
    <0x0D>
    0.66
    -
    0.66
    ,
    0.66
     successive
    0.64
    )
    0.63
     philosoph
    0.61
    をご覧ください
    0.61
     이러한
    0.61
     puzzled
    0.61
    POSITIVE LOGITS
     엄청
    0.71
     চাহিল
    0.63
    オプション
    0.62
     donate
    0.59
     너무
    0.59
     ஏற்ப
    0.59
     उनको
    0.59
     removes
    0.58
    帮忙
    0.57
     kemarin
    0.57
    Activations Density 0.227%

    No Known Activations