© 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. 133224
    Prev
    Next
    INDEX
    Explanations

    word / token endings

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

    provoking mild

    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
     Boone
    0.50
     Literacy
    0.47
     Clothes
    0.47
    തിനാ
    0.47
    דים
    0.46
    ’।
    0.46
    šu
    0.45
    '].'
    0.45
    ’
    0.45
     laud
    0.45
    POSITIVE LOGITS
    h
    0.51
    !"));
    0.50
    u
    0.49
    um
    0.46
     दिनेश
    0.46
    t
    0.46
    ه
    0.46
    gå
    0.45
     කො
    0.45
     renormalization
    0.45
    Activations Density 0.000%

    No Known Activations