© 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. 22-GEMMASCOPE-RES-131K
    7. 65166
    Prev
    Next
    INDEX
    Explanations

    code paths and system components

    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_22/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
    ledad
    -0.93
    恐惧
    -0.92
    legte
    -0.91
    龔
    -0.91
    相変わらず
    -0.90
    ckeye
    -0.88
    追記
    -0.88
    =#{
    -0.88
     pilotes
    -0.86
    Ҡ
    -0.86
    POSITIVE LOGITS
     functions
    1.11
     operations
    1.10
     tools
    1.09
     settings
    1.05
     dynamics
    1.03
     resources
    1.03
     life
    1.03
    MISC
    1.00
     structure
    1.00
     management
    0.99
    Activations Density 0.020%

    No Known Activations