© 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. 120750
    Prev
    Next
    INDEX
    Explanations

    locations, things, or actions

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

    what deserves success

    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
    વી
    0.45
     Somm
    0.45
    esso
    0.43
     slavery
    0.42
    btns
    0.42
    삶
    0.42
     pria
    0.40
    commerce
    0.40
    אָ
    0.40
     tunn
    0.39
    POSITIVE LOGITS
     অত্যন্ত
    0.43
     এছাড়া
    0.43
    ('['
    0.42
     Highly
    0.42
    ியுடன்
    0.41
    配合
    0.41
     ഇവ
    0.41
    pection
    0.41
     値
    0.41
     kutoka
    0.40
    Activations Density 0.001%

    No Known Activations