© 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. 112973
    Prev
    Next
    INDEX
    Explanations

    define and create

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

    automatically adjust

    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
    Ki
    0.49
    ร
    0.48
    诺
    0.48
    дея
    0.47
    Innen
    0.46
    汽车
    0.45
    비
    0.45
    蜜
    0.45
    Original
    0.45
    hte
    0.44
    POSITIVE LOGITS
     mantenere
    0.54
     aclarar
    0.52
     intercal
    0.52
    味が
    0.47
     mantener
    0.47
    imcoords
    0.46
     manteniendo
    0.46
     dxc
    0.44
     menjadikan
    0.44
     aclar
    0.44
    Activations Density 0.000%

    No Known Activations