© 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. 78315
    Prev
    Next
    INDEX
    Explanations

    died Monday

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

    specific terms and their descriptions

    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
    ه
    0.55
    ი
    0.50
    .
    0.46
    ,*
    0.46
    *.
    0.46
    ните
    0.45
    ي
    0.45
    جد
    0.44
    ORIG
    0.44
     акции
    0.43
    POSITIVE LOGITS
    ார
    0.52
     গিয়াছেন
    0.46
    liess
    0.46
     ラウンド
    0.46
     রাধানাথ
    0.45
    miot
    0.45
    ದಗ
    0.45
    cí
    0.45
     assurent
    0.44
    ார்
    0.44
    Activations Density 0.000%

    No Known Activations