© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3798
    Prev
    Next
    INDEX
    Explanations

    former, latter, last

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

    The neuron is strongly activated by occurrences of the phrase “the latter.”

    oai_token-act-pair · o4-miniTriggered 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
    or
    0.72
    il
    0.68
    0.66
    ima
    0.64
    vo
    0.63
    ol
    0.61
    this
    0.61
    ir
    0.60
     a
    0.60
     seluruh
    0.59
    POSITIVE LOGITS
     purportedly
    0.76
     suscit
    0.72
     latter
    0.66
    可通过
    0.66
     تتم
    0.61
     sidelined
    0.60
     النقطه
    0.60
     ascribed
    0.59
    钥
    0.59
    <unused2162>
    0.59
    Activations Density 0.015%

    No Known Activations