© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14795
    Prev
    Next
    INDEX
    Explanations

    section titles

    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_22/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
    戆
    -2.56
    亖
    -2.48
    蚍
    -2.47
    を活用
    -2.31
    髫
    -2.30
    猡
    -2.30
    ࿊
    -2.30
    蚡
    -2.28
    geſ
    -2.27
     ſuch
    -2.25
    POSITIVE LOGITS
    as
    2.73
    This
    2.69
     Therefore
    2.66
     Whereas
    2.59
    IN
    2.56
     the
    2.55
    With
    2.47
     Until
    2.45
     Этот
    2.44
    ،
    2.44
    Activations Density 0.044%

    No Known Activations