© 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. 211135
    Prev
    Next
    INDEX
    Explanations

    protecting and safeguarding your

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

    playing with words

    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
    M
    0.49
    Cash
    0.49
    WEST
    0.49
     CASH
    0.46
    LIE
    0.46
    EW
    0.44
    CSS
    0.44
    MIL
    0.44
    OUT
    0.44
     and
    0.43
    POSITIVE LOGITS
    طلب
    0.59
    
    0.55
    ยาก
    0.54
    に必要な
    0.53
    گذ
    0.52
    নৈতিক
    0.52
     เข
    0.52
    ScriptBuf
    0.50
    ήμε
    0.50
    illä
    0.49
    Activations Density 0.000%

    No Known Activations