© 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. 16148
    Prev
    Next
    INDEX
    Explanations

    property name assignment json

    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
    toPromise
    -0.99
     of
    -0.92
     reminds
    -0.88
    他に
    -0.82
    ">...
    -0.82
     अपनी
    -0.82
    
    -0.82
     explique
    -0.80
    drá
    -0.80
     action
    -0.77
    POSITIVE LOGITS
    atized
    1.06
    Lø
    1.04
    viel
    1.02
    gleichen
    1.00
    DebuggerNonUser
    0.99
    在這
    0.96
    ਫ਼
    0.96
     dáms
    0.95
    recognized
    0.93
    ⢤
    0.92
    Activations Density 0.002%

    No Known Activations