© 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. 39903
    Prev
    Next
    INDEX
    Explanations

    discussing what to ask/earn/style

    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
    ="/"
    0.46
    潘
    0.44
    кир
    0.43
    áculos
    0.42
    低
    0.42
    ุน
    0.41
    каче
    0.41
    デメリット
    0.41
    ាល់
    0.40
    ंत्रिक
    0.40
    POSITIVE LOGITS
     své
    0.59
     Zwe
    0.48
     対
    0.48
     vergangenen
    0.47
     東京
    0.47
     następnie
    0.46
     svých
    0.45
     aritmética
    0.45
     Verhältnis
    0.45
     svoje
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.