© 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. 59013
    Prev
    Next
    INDEX
    Explanations

    @author tags in comments

    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
    ELECTRIC
    -1.51
    ニメ
    -1.48
    ופי
    -1.47
     belangrijke
    -1.38
    ToDecimal
    -1.38
     guantes
    -1.37
     benötigt
    -1.37
     klucz
    -1.30
     viktig
    -1.28
    ataires
    -1.27
    POSITIVE LOGITS
     There
    1.76
     should
    1.69
     we
    1.59
    There
    1.59
    They
    1.47
     before
    1.42
     there
    1.41
    there
    1.40
     has
    1.39
     Although
    1.38
    Activations Density 0.034%

    No Known Activations