© 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. 196137
    Prev
    Next
    INDEX
    Explanations

    car rental and conventions

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

    economic, performance, affordable, demanded, self, integration

    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
    𒄑
    0.52
    lytres
    0.52
    kfollowers
    0.50
     промо
    0.48
     保護
    0.48
     proteção
    0.48
     回転
    0.47
    ர்ஸ்
    0.47
    opold
    0.47
    рог
    0.46
    POSITIVE LOGITS
    เป็น
    0.54
    ing
    0.52
    ,
    0.49
     and
    0.47
    '
    0.47
    ual
    0.47
    uality
    0.46
    이
    0.45
    at
    0.45
    al
    0.45
    Activations Density 0.001%

    No Known Activations