© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12324
    Prev
    Next
    INDEX
    Explanations

    haven followed by positive statement

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

    code identifiers and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     sécrétion
    0.41
    aroos
    0.40
     thiệt
    0.38
     altre
    0.38
    吅
    0.38
     arra
    0.37
     annunci
    0.37
    ফলে
    0.37
     BUREAU
    0.36
     Arran
    0.36
    POSITIVE LOGITS
    Quick
    0.38
    Criteria
    0.38
    Bennett
    0.37
    Genesis
    0.36
    밸
    0.34
    Mode
    0.34
    MenuView
    0.34
    Live
    0.34
    Tomorrow
    0.34
    Hi
    0.33
    Activations Density 0.007%

    No Known Activations