© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19489
    Prev
    Next
    INDEX
    Explanations

    named entities and abbreviations

    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
    </h5>
    -2.78
     Saltar
    -2.75
    us
    -2.72
    亟
    -2.59
    </td>
    -2.53
     are
    -2.45
    ଃ
    -2.36
    푙
    -2.34
    》，
    -2.33
    }$,
    -2.31
    POSITIVE LOGITS
     they
    2.59
    i
    2.55
    </strong>
    2.55
    1
    2.53
    ي
    2.50
    那我
    2.39
    י
    2.36
    ﾁ
    2.31
    出来ました
    2.30
     anunciar
    2.19
    Activations Density 0.034%

    No Known Activations