© 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. 102618
    Prev
    Next
    INDEX
    Explanations

    "so" followed by adjective

    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
    )$,
    -1.55
    𖥦
    -1.38
    риях
    -1.36
     giebt
    -1.34
    //!
    -1.34
    趼
    -1.31
     môžete
    -1.28
    ୯
    -1.28
    ikasi
    -1.27
    detek
    -1.27
    POSITIVE LOGITS
     other
    1.64
     solchen
    1.54
    ol
    1.47
    螃
    1.36
     not
    1.31
     others
    1.28
    _
    1.27
    たまたま
    1.27
    ate
    1.26
    te
    1.20
    Activations Density 0.010%

    No Known Activations