© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 69678
    Prev
    Next
    INDEX
    Explanations

    most common listings and types

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

    most common or frequent examples

    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
    /
    0.50
    @
    0.49
    :
    0.48
    \
    0.47
    -
    0.46
     безопасности
    0.45
     Dun
    0.41
    oz
    0.40
    zeta
    0.40
    +
    0.40
    POSITIVE LOGITS
     그러니까
    0.46
     أغ
    0.46
     व्यक्ती
    0.45
     захворю
    0.45
     znovu
    0.43
    স্যা
    0.42
     منظر
    0.42
    인데
    0.41
     adicion
    0.40
     সংক্রম
    0.40
    Activations Density 0.003%

    No Known Activations