© 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. 128140
    Prev
    Next
    INDEX
    Explanations

    hundreds of thousands

    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
     Recognizing
    -2.08
     Allowing
    -2.02
     Yet
    -2.02
    蠵
    -1.99
     Coupled
    -1.98
     容量
    -1.95
    θο
    -1.95
     Feeling
    -1.95
     Utilizing
    -1.95
     Hoping
    -1.93
    POSITIVE LOGITS
    </em>
    2.45
     have
    2.39
     or
    1.95
    ’
    1.91
     government
    1.91
    تیجه
    1.85
    russia
    1.76
    </h3>
    1.73
    </strong>
    1.68
    σει
    1.66
    Activations Density 0.002%

    No Known Activations