© 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. 139397
    Prev
    Next
    INDEX
    Explanations

    abdomen, hands, periods

    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
     hasil
    0.50
    ць
    0.43
    WERS
    0.43
     ambiance
    0.42
     replies
    0.41
     conseguir
    0.41
    叧
    0.41
     deix
    0.40
     aftermath
    0.39
     kehadiran
    0.39
    POSITIVE LOGITS
    ješ
    0.40
    {\
    0.39
    fmt
    0.39
    space
    0.39
    umble
    0.39
    Simulator
    0.38
    ∎
    0.38
    rell
    0.38
    ក្នុង
    0.38
    nim
    0.38
    Activations Density 0.001%

    No Known Activations