© 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. 250447
    Prev
    Next
    INDEX
    Explanations

    JSON data formats

    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
    Negative Logits
    d
    0.96
    y
    0.84
    dose
    0.68
    mec
    0.67
    dala
    0.65
     формула
    0.65
    manu
    0.64
    yaj
    0.64
    vian
    0.63
    ノール
    0.62
    POSITIVE LOGITS
    ่
    0.86
    ре
    0.73
    يت
    0.73
    ма
    0.71
     spezielle
    0.71
    א
    0.70
    או
    0.70
    ро
    0.68
    ट
    0.68
    м
    0.67
    Activations Density 0.000%

    No Known Activations