© 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. 9106
    Prev
    Next
    INDEX
    Explanations

    list items

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

    This neuron fires on the last content token just before a segment’s end boundary.

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

    periods at the end of sentences or sections in formal/technical text.

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

    nouns functioning as objects of prepositions, especially concrete places or event/time terms.

    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
    ্তার
    0.58
     applaud
    0.57
     Councilor
    0.55
     Whitley
    0.52
     With
    0.52
     Walking
    0.52
     atas
    0.52
    凭借
    0.51
     Shreveport
    0.51
     Boardwalk
    0.51
    POSITIVE LOGITS
     lingü
    0.55
     או
    0.52
     సన్ని
    0.51
     različ
    0.50
    
    0.49
     nebo
    0.48
     காட்ச
    0.47
    หรือ
    0.47
     rectángulo
    0.47
     күз
    0.47
    Activations Density 0.051%

    No Known Activations