© 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. 63856
    Prev
    Next
    INDEX
    Explanations

    chose Database

    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
     જરૂ
    0.53
     ίδια
    0.53
     fechas
    0.52
     indicado
    0.48
     descripción
    0.48
     ଜ
    0.48
     intensidad
    0.47
    }^{+},
    0.46
     ubicado
    0.46
     señalado
    0.45
    POSITIVE LOGITS
    ه
    0.52
    ה
    0.50
     communities
    0.46
    سپ
    0.43
     residents
    0.43
    ע
    0.43
     heroes
    0.42
     Spro
    0.42
    SEP
    0.42
    اتب
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.