© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138928
    Prev
    Next
    INDEX
    Explanations

    religious holidays, legal cases, restoration, screening, artists

    np_acts-logits-general · gemini-2.5-flash-lite

    cell A, sacrificing efficiency, various technologies, Explain Value, clustered around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PRES
    0.56
    седнев
    0.52
    IONES
    0.50
    AMENTO
    0.50
     ciento
    0.50
     esfuerzos
    0.50
    ן
    0.48
     empleado
    0.48
    ровала
    0.48
     intentos
    0.48
    POSITIVE LOGITS
     Speak
    0.54
     Thank
    0.50
    ell
    0.50
     Kick
    0.47
    Speak
    0.47
     Wheat
    0.46
    Churn
    0.46
    끔
    0.45
    eek
    0.44
     Bike
    0.44
    Activations Density 0.001%

    No Known Activations