© 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. 105913
    Prev
    Next
    INDEX
    Explanations

    bug report

    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
     by
    -1.93
     because
    -1.75
     using
    -1.63
     through
    -1.60
     after
    -1.58
     when
    -1.57
     if
    -1.53
     this
    -1.48
    </b>
    -1.47
     an
    -1.45
    POSITIVE LOGITS
     relativement
    1.63
    訫
    1.60
    relatively
    1.52
     permettant
    1.49
    nine
    1.49
     apparente
    1.48
    apparently
    1.45
    never
    1.45
    ynchronously
    1.44
    让
    1.43
    Activations Density 0.002%

    No Known Activations