© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100365
    Prev
    Next
    INDEX
    Explanations

    daily occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aident
    -1.65
     rendent
    -1.59
     mohou
    -1.56
    憔
    -1.55
     donnent
    -1.55
    ність
    -1.55
    忖
    -1.53
     刺繍
    -1.52
     ahora
    -1.51
    麿
    -1.51
    POSITIVE LOGITS
     telefónica
    2.09
    "
    1.97
    The
    1.95
    When
    1.95
    ～～～～
    1.92
    4
    1.90
    一套
    1.88
    With
    1.84
    0
    1.81
    You
    1.80
    Activations Density 0.022%

    No Known Activations