© 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. 22460
    Prev
    Next
    INDEX
    Explanations

    during which

    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
     =
    -1.91
    1
    -1.86
    6
    -1.78
    e
    -1.73
    a
    -1.71
    即便是
    -1.71
    v
    -1.71
    5
    -1.62
    x
    -1.62
    D
    -1.61
    POSITIVE LOGITS
     which
    3.70
     that
    2.31
     whom
    2.23
     bekom
    1.90
     hvis
    1.83
     konkrete
    1.83
     οπο
    1.78
    iornamento
    1.76
    </h5>
    1.73
     которым
    1.70
    Activations Density 0.053%

    No Known Activations