© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13211
    Prev
    Next
    INDEX
    Explanations

    violence hotline, ethics committee, claims act, inspection code, cistern adhesions, mobility programme

    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_65k_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
    勇敢
    0.34
     It
    0.34
    ::{
    0.33
     it
    0.33
    ipment
    0.33
     _:
    0.33
    ুদের
    0.33
     In
    0.33
    Deterministic
    0.33
    에
    0.32
    POSITIVE LOGITS
     അ
    0.34
    owego
    0.34
    FBSDKGraph
    0.33
    Ꭺ
    0.33
    कालय
    0.33
    רג
    0.32
     者
    0.32
    راك
    0.32
    קו
    0.32
    rieb
    0.31
    Activations Density 0.216%

    No Known Activations