© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85663
    Prev
    Next
    INDEX
    Explanations

    new followed by noun

    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
     )(
    -1.43
    消失了
    -1.41
     }.
    -1.35
     iemand
    -1.35
     Jeden
    -1.27
     ono
    -1.27
    手机号
    -1.27
     noy
    -1.26
     behand
    -1.25
     exis
    -1.25
    POSITIVE LOGITS
    '
    1.41
     a
    1.34
    </h1>
    1.34
     about
    1.30
    liegenden
    1.25
    </h5>
    1.23
     before
    1.20
    </b>
    1.16
     德
    1.16
     designated
    1.15
    Activations Density 0.028%

    No Known Activations