© 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. 77149
    Prev
    Next
    INDEX
    Explanations

    offers and benefits

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

    El jefe

    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
    𝓈
    0.52
    ۱۹
    0.51
    𝕂
    0.50
     !***
    0.48
    Ꮺ
    0.47
    deload
    0.46
     claust
    0.46
    。
    0.46
    ユーザー
    0.46
    实质
    0.46
    POSITIVE LOGITS
    ardini
    0.47
     Ol
    0.46
     pontos
    0.45
     Cultura
    0.44
     Sauv
    0.44
    el
    0.44
     jefe
    0.44
     wür
    0.43
     El
    0.43
    umen
    0.42
    Activations Density 0.000%

    No Known Activations