© 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. 22-GEMMASCOPE-RES-131K
    7. 34667
    Prev
    Next
    INDEX
    Explanations

    class field declarations

    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_22/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
     secondly
    -1.20
    wilson
    -1.05
    uito
    -1.02
    tative
    -0.98
     ТАК
    -0.98
     also
    -0.97
    antre
    -0.96
    pshire
    -0.96
    dence
    -0.95
    了一会儿
    -0.94
    POSITIVE LOGITS
     hech
    1.13
     mej
    1.00
     belga
    0.92
    蕯
    0.92
    んだよね
    0.90
    elle
    0.88
    </tbody>
    0.88
     daban
    0.88
     rêver
    0.87
    让他们
    0.86
    Activations Density 0.011%

    No Known Activations