© 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. 86079
    Prev
    Next
    INDEX
    Explanations

    items and services

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

    competitors, code, confidence, ocean, Android

    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
    9
    0.41
    acus
    0.40
    當時
    0.40
    当時の
    0.39
    7
    0.38
    -
    0.38
    шлось
    0.38
    邸
    0.37
    ById
    0.37
    当时
    0.37
    POSITIVE LOGITS
     Entwick
    0.49
     dobbiamo
    0.48
     lovely
    0.47
     stato
    0.46
     vouloir
    0.45
     destinada
    0.45
     debemos
    0.45
     dreamy
    0.45
     devemos
    0.44
     Ró
    0.44
    Activations Density 0.002%

    No Known Activations