© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77410
    Prev
    Next
    INDEX
    Explanations

    java.util.logging.Level

    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
     people
    -0.94
    @~
    -0.92
     during
    -0.89
     until
    -0.82
    kDa
    -0.80
    の関係
    -0.79
    غم
    -0.79
     before
    -0.76
     nearly
    -0.74
     in
    -0.73
    POSITIVE LOGITS
     level
    1.35
    niveau
    1.27
     Level
    1.23
     niveau
    1.16
     livello
    1.15
     SEVER
    1.15
    level
    1.14
     уровень
    1.12
    Level
    1.09
     niveaux
    1.07
    Activations Density 0.000%

    No Known Activations