© 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. 40248
    Prev
    Next
    INDEX
    Explanations

    permission is granted

    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
    {
    -2.88
    耜
    -2.81
    ignements
    -2.41
    𖧵
    -2.41
    ᥬ
    -2.38
    剁
    -2.34
    ᠊
    -2.34
     עם
    -2.33
     проекта
    -2.25
    翃
    -2.25
    POSITIVE LOGITS
    This
    3.34
    It
    3.00
     Their
    2.98
    "
    2.89
    縂
    2.88
     були
    2.80
    which
    2.75
    We
    2.73
    there
    2.66
    There
    2.63
    Activations Density 0.007%

    No Known Activations