© 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. 68356
    Prev
    Next
    INDEX
    Explanations

    addresses and affiliations

    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
    .
    -2.34
    </em>
    -2.16
     meditative
    -1.96
     longstanding
    -1.89
     装着
    -1.81
    $\$$
    -1.80
    </b>
    -1.79
     Warszawie
    -1.73
     dodgy
    -1.70
     Krakowie
    -1.69
    POSITIVE LOGITS
    ㈯
    2.33
     alza
    2.31
     なん
    2.30
     necessario
    2.30
    does
    2.20
     interessa
    2.17
    ﹍﹍
    2.16
    蹓
    2.14
     allarg
    2.13
     know
    2.11
    Activations Density 0.002%

    No Known Activations