© 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. 65238
    Prev
    Next
    INDEX
    Explanations

    @ followed by command or directive

    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
     also
    -1.88
     they
    -1.82
     "
    -1.68
    or
    -1.58
     अपने
    -1.57
    </h5>
    -1.54
    on
    -1.53
    ……….
    -1.47
    ….
    -1.47
    for
    -1.45
    POSITIVE LOGITS
    是因为
    1.59
    どうやら
    1.53
     ilumina
    1.48
    lognese
    1.48
    鴴
    1.48
     silueta
    1.45
     głó
    1.45
    assemblée
    1.44
     pouce
    1.44
     gustado
    1.44
    Activations Density 0.012%

    No Known Activations