© 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. 104128
    Prev
    Next
    INDEX
    Explanations

    testing and measurement contexts

    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
    「
    -2.20
    and
    -2.02
    ，「
    -1.91
    ：「
    -1.84
    </td>
    -1.77
     Incidentally
    -1.75
     Presumably
    -1.73
     However
    -1.72
    “
    -1.71
     Naturally
    -1.70
    POSITIVE LOGITS
    橚
    1.87
     refugi
    1.80
     větší
    1.77
     bordados
    1.75
    --"
    1.74
    𓐍
    1.72
     anún
    1.70
    澌
    1.70
     különböző
    1.69
    —"
    1.67
    Activations Density 0.012%

    No Known Activations