© 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. 142350
    Prev
    Next
    INDEX
    Explanations

    mistakes, adoption, and write

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

    Drive Activity, once the, effectively functions

    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
     Österreich
    0.45
     Quảng
    0.44
    〉
    0.44
     Пас
    0.43
    venta
    0.43
    🚻
    0.42
     மேற்பர
    0.42
     gourd
    0.41
     குழு
    0.41
     Broadcasting
    0.41
    POSITIVE LOGITS
     parallels
    0.51
     tangents
    0.50
     따
    0.49
     laughs
    0.49
    ื่อ
    0.48
     chills
    0.48
    ଲା
    0.47
    щення
    0.46
    心里
    0.46
     이후
    0.46
    Activations Density 0.000%

    No Known Activations