© 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. 103169
    Prev
    Next
    INDEX
    Explanations

    bringing up

    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
    </td>
    -3.03
    <
    -2.83
    ),
    -2.61
    [
    -2.22
    </h5>
    -2.20
    ",
    -2.19
     "
    -2.19
    ...
    -2.13
    </
    -2.08
    </b>
    -2.06
    POSITIVE LOGITS
    maphore
    1.96
     inmediatamente
    1.95
     extensive
    1.91
    妧
    1.85
    chloric
    1.78
     fabricants
    1.77
    alers
    1.73
    vellous
    1.73
    gherita
    1.71
    娥
    1.70
    Activations Density 0.003%

    No Known Activations