© 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. 84669
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations

    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
     from
    -1.91
     for
    -1.89
     which
    -1.88
     and
    -1.83
     of
    -1.80
     by
    -1.73
     one
    -1.73
     both
    -1.66
     at
    -1.52
     these
    -1.49
    POSITIVE LOGITS
    4
    1.91
    9
    1.75
     astounding
    1.70
    3
    1.66
    2
    1.65
    6
    1.64
    5
    1.62
    焼く
    1.61
    uded
    1.57
    7
    1.57
    Activations Density 0.008%

    No Known Activations