© 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. 256818
    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
    इन
    0.45
    все
    0.45
    вари
    0.43
    चान
    0.43
     When
    0.43
    сус
    0.43
     </
    0.42
    सन
    0.42
    ට්ට
    0.41
     variabili
    0.41
    POSITIVE LOGITS
    ম
    0.43
     Diageo
    0.43
     lube
    0.41
    ••••
    0.41
     konu
    0.41
     attrakt
    0.41
    chemia
    0.41
    ứng
    0.40
    ByteBuffer
    0.39
     molle
    0.39
    Activations Density 0.001%

    No Known Activations