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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32962
    Prev
    Next
    INDEX
    Explanations

    punctuation or structural separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     попула
    0.52
     सिद्धांतों
    0.51
    ):["
    0.47
     युवाओ
    0.47
     సాధ
    0.47
     ప్రే
    0.47
     укра
    0.47
     ON
    0.46
     DURING
    0.46
    蹈
    0.46
    POSITIVE LOGITS
    {
    0.53
     kalor
    0.47
     Hadid
    0.47
     {
    0.46
     opp
    0.46
    t
    0.46
     (
    0.45
     famili
    0.45
    bet
    0.44
    ofthe
    0.44
    Activations Density 0.004%

    No Known Activations