© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104155
    Prev
    Next
    INDEX
    Explanations

    key-value assignments

    np_acts-logits-general · gemini-2.5-flash-lite

    property or parameter names in code (especially in camelCase or PascalCase format).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     and
    -1.88
     participado
    -1.80
    ουμε
    -1.53
    obut
    -1.48
     situe
    -1.46
     will
    -1.43
     atau
    -1.42
    كويكب
    -1.41
     conseguido
    -1.37
     our
    -1.32
    POSITIVE LOGITS
    :
    2.63
     its
    1.79
    Its
    1.67
    </strong>
    1.56
    </b>
    1.48
     (
    1.47
    を行います
    1.44
    其
    1.42
    д
    1.41
    作って
    1.38
    Activations Density 0.069%

    No Known Activations