© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86936
    Prev
    Next
    INDEX
    Explanations

    modified and complete

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

    problem after

    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
     funzionamento
    0.46
     combina
    0.42
    確立
    0.42
     nonzero
    0.41
    데요
    0.41
    ⺈
    0.41
    还有
    0.40
    下次
    0.40
    longmapsto
    0.40
    స్తూ
    0.40
    POSITIVE LOGITS
    uluh
    0.46
    ="";
    0.46
    ută
    0.45
     नारा
    0.45
    ukes
    0.44
    celona
    0.43
    <
    0.43
    ukkh
    0.43
    ;<
    0.43
    erà
    0.43
    Activations Density 0.001%

    No Known Activations