© 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. 970
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    a
    0.55
    TECHN
    0.55
    in
    0.53
    i
    0.53
    ي
    0.51
     ሁ
    0.49
    Fa
    0.48
    အတွ
    0.48
    techn
    0.48
    ه
    0.48
    POSITIVE LOGITS
    abileceğ
    0.44
    acas
    0.44
    malı
    0.43
     Sincerely
    0.42
     CARBON
    0.42
    gum
    0.41
     lojas
    0.41
     গেরিলারা
    0.40
     buenas
    0.40
    क्रोश
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.