© 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. 236438
    Prev
    Next
    INDEX
    Explanations

    system status, keeping hydrated, compiled lists

    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
     ましょう
    0.55
     суще
    0.52
    >**
    0.52
    agamanam
    0.51
     гель
    0.50
    LayoutPanel
    0.50
     açı
    0.48
    ^*(\
    0.48
     অর্চনা
    0.48
    বিধান
    0.48
    POSITIVE LOGITS
    는
    0.47
    Fortunately
    0.46
     Lorsque
    0.43
     This
    0.42
     Rename
    0.42
     pouvez
    0.42
     Kalau
    0.41
    reya
    0.41
     BCG
    0.41
     Fortunately
    0.41
    Activations Density 0.000%

    No Known Activations