© 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. 41283
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    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
    </h3>
    -2.73
     =
    -2.23
    \
    -2.09
    </i>
    -2.06
     &
    -1.95
    ン
    -1.78
    </em>
    -1.76
     –
    -1.70
    }$,
    -1.69
    "))
    -1.62
    POSITIVE LOGITS
     the
    2.22
     encontrará
    1.79
     precisar
    1.66
    Transcripción
    1.59
     napraw
    1.58
     vertre
    1.57
     lembra
    1.56
    Transcriptie
    1.55
     acredita
    1.54
     it
    1.53
    Activations Density 0.000%

    No Known Activations