© 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. 10-GEMMASCOPE-RES-131K
    7. 8770
    Prev
    Next
    INDEX
    Explanations

    linking two items

    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
     
    -2.22
     vielleicht
    -1.86
     delightfully
    -1.81
     unending
    -1.71
     uniquement
    -1.70
     REALLY
    -1.69
     decidedly
    -1.67
    ↵↵
    -1.63
     exceedingly
    -1.61
     sumptuous
    -1.61
    POSITIVE LOGITS
     with
    2.41
     at
    2.39
     both
    2.20
     to
    2.16
     this
    2.09
     what
    2.03
     from
    2.03
     after
    1.94
     that
    1.90
     two
    1.90
    Activations Density 0.046%

    No Known Activations