© 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. 72782
    Prev
    Next
    INDEX
    Explanations

    Robert Avery

    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
    קישורים
    -1.02
     llavero
    -1.00
     despite
    -1.00
    thenReturn
    -0.98
     Fotos
    -0.96
    providedIn
    -0.93
     осте
    -0.91
    хані
    -0.90
    arashtra
    -0.90
    terase
    -0.87
    POSITIVE LOGITS
     државе
    1.07
     kochen
    0.99
    で使用
    0.97
    artiste
    0.95
     offrire
    0.92
     CLO
    0.90
    Databases
    0.90
     zubere
    0.89
     HOC
    0.88
    ཨ
    0.88
    Activations Density 0.000%

    No Known Activations