© 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. 71206
    Prev
    Next
    INDEX
    Explanations

    dragon and Chinese names

    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
    0
    -3.59
    y
    -3.44
    </strong>
    -3.38
    >
    -2.50
    [
    -2.48
    According
    -2.45
    This
    -2.42
    c
    -2.41
    4
    -2.39
    ing
    -2.30
    POSITIVE LOGITS
    </td>
    2.77
    </b>
    2.41
    璈
    2.22
    夤
    2.19
    ſſen
    2.19
    felpa
    2.09
     znal
    2.08
     avid
    2.06
    锖
    2.03
    鳔
    1.98
    Activations Density 0.006%

    No Known Activations