© 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. 51463
    Prev
    Next
    INDEX
    Explanations

    specificity and variation

    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
     and
    0.55
     pokemon
    0.46
     Pokemon
    0.46
     Guernsey
    0.44
     sorted
    0.43
     모든
    0.43
     but
    0.43
    t
    0.42
    th
    0.42
     AND
    0.42
    POSITIVE LOGITS
    гти
    0.50
    ంద
    0.49
     específicas
    0.48
     específica
    0.46
     spezif
    0.46
    бар
    0.46
     stärker
    0.46
     específicos
    0.44
     berücksicht
    0.44
     específico
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.