© 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. 22318
    Prev
    Next
    INDEX
    Explanations

    introduces or follows transitions

    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
     in
    -1.71
     for
    -1.64
    着一
    -1.46
    дис
    -1.45
     can
    -1.36
    uerst
    -1.34
     mío
    -1.34
     only
    -1.32
    StateToProps
    -1.32
    %,
    -1.30
    POSITIVE LOGITS
    although
    1.47
     these
    1.46
    廰
    1.45
    jeuner
    1.43
     accla
    1.42
     ſeveral
    1.42
     theſe
    1.41
     that
    1.41
     musíte
    1.41
    .”.
    1.41
    Activations Density 0.267%

    No Known Activations