© 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. 151593
    Prev
    Next
    INDEX
    Explanations

    she will, maintained low

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

    PHP Models, Http, Services

    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
    जि
    0.48
    イス
    0.46
    推進
    0.45
    лі
    0.45
    עת
    0.45
     geography
    0.45
    ხ
    0.45
    ク
    0.44
    зи
    0.44
    atividade
    0.44
    POSITIVE LOGITS
     ولم
    0.44
    BrNO
    0.44
    PPI
    0.43
    Parsed
    0.43
    CMI
    0.43
     것이
    0.43
     چون
    0.42
    ILLA
    0.42
    过来的
    0.42
    AMM
    0.42
    Activations Density 0.000%

    No Known Activations