© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117589
    Prev
    Next
    INDEX
    Explanations

    requirements and availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sock
    -0.80
     embracing
    -0.77
     yii
    -0.76
     after
    -0.75
    、《
    -0.73
     jTextField
    -0.73
     avoiding
    -0.72
    ZIONE
    -0.71
     potentially
    -0.71
     oman
    -0.71
    POSITIVE LOGITS
    requires
    0.90
    requ
    0.80
     Änderungen
    0.76
     préstamo
    0.75
    😴
    0.74
    ῤ
    0.74
    bezirk
    0.73
    mortem
    0.73
     murales
    0.73
     espacios
    0.71
    Activations Density 0.001%

    No Known Activations