© 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. 21974
    Prev
    Next
    INDEX
    Explanations

    initial word fragments

    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
    a
    -3.91
    d
    -2.97
    咴
    -2.92
     fortsatt
    -2.92
    VERY
    -2.88
     tía
    -2.80
     tjen
    -2.77
    鈇
    -2.77
    鉏
    -2.72
     interessant
    -2.64
    POSITIVE LOGITS
     divinely
    2.66
    ꦫ
    2.59
    When
    2.48
    *)((
    2.44
     stupe
    2.41
    Despite
    2.34
     disconcer
    2.33
     Primarily
    2.33
    IANT
    2.33
     teilweise
    2.33
    Activations Density 0.021%

    No Known Activations