© 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. 111702
    Prev
    Next
    INDEX
    Explanations

    at least X

    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
    存知
    -2.50
    ඬ
    -2.36
     Currently
    -2.33
    MediaStore
    -2.31
    quait
    -2.28
    𖥧
    -2.28
     покупки
    -2.27
    Ꭸ
    -2.14
     Anpass
    -2.11
     Our
    -2.09
    POSITIVE LOGITS
    s
    3.38
    "
    3.02
    '
    2.92
    at
    2.55
    IGRATION
    2.42
    <bos>
    2.42
    梣
    2.38
    fusions
    2.22
    line
    2.20
    vaded
    2.19
    Activations Density 0.014%

    No Known Activations