© 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. 71823
    Prev
    Next
    INDEX
    Explanations

    matrix

    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
     Our
    -2.84
     dejected
    -2.78
     Slightly
    -2.58
    ’
    -2.58
    ญี่ป
    -2.56
     These
    -2.50
    就像是
    -2.48
    耜
    -2.48
     aching
    -2.48
     Regarding
    -2.48
    POSITIVE LOGITS
    镚
    2.63
     silencioso
    2.59
    现在的
    2.56
     hvem
    2.53
     vivido
    2.50
    鉝
    2.45
     your
    2.44
     decorado
    2.36
    他也
    2.34
     saada
    2.33
    Activations Density 0.009%

    No Known Activations