© 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. 34092
    Prev
    Next
    INDEX
    Explanations

    Alternative Characters

    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
    zył
    -0.93
     trayectoria
    -0.88
    szám
    -0.88
     kalend
    -0.86
     eksempel
    -0.84
     okul
    -0.84
     Havana
    -0.84
    cotton
    -0.84
    ulose
    -0.82
    ICALLY
    -0.82
    POSITIVE LOGITS
     again
    0.81
     уже
    0.79
     işte
    0.77
     gelas
    0.77
     difícil
    0.77
    可以
    0.76
     refaire
    0.76
    년
    0.76
     опять
    0.75
     feier
    0.75
    Activations Density 0.041%

    No Known Activations