© 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. 8314
    Prev
    Next
    INDEX
    Explanations

    get at, had in, after some

    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
    軼
    -1.95
    5
    -1.84
    9
    -1.81
     the
    -1.72
    欵
    -1.69
    3
    -1.62
    </tfoot>
    -1.61
    With
    -1.59
     αυτά
    -1.59
     fourteen
    -1.58
    POSITIVE LOGITS
     disfru
    1.75
    âneo
    1.67
     asomb
    1.67
    槐
    1.65
     elicit
    1.63
     empê
    1.62
    ejercicio
    1.62
    mme
    1.61
    茎
    1.59
    穑
    1.59
    Activations Density 0.003%

    No Known Activations