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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1707
    Prev
    Next
    INDEX
    Explanations

    disappearing into

    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
     M
    0.35
     V
    0.35
     P
    0.35
    Neue
    0.34
    ใหม่
    0.33
     Neue
    0.33
    ப
    0.32
    Am
    0.32
     smoot
    0.32
    コン
    0.31
    POSITIVE LOGITS
     justiciable
    0.38
     conductas
    0.35
     referido
    0.34
    <unused96>
    0.34
     مذکور
    0.33
     sufficient
    0.32
     difíc
    0.32
     occasioned
    0.32
     demonstrable
    0.31
    െന്ന്
    0.31
    Activations Density 0.000%

    No Known Activations