© 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. 22-GEMMASCOPE-RES-131K
    7. 38643
    Prev
    Next
    INDEX
    Explanations

    range or uncertainty

    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_22/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
    0
    -2.39
     membantu
    -1.98
     #(
    -1.84
    ">
    -1.73
     устройств
    -1.70
    骉
    -1.69
    -------
    -1.63
     efforts
    -1.62
    などを
    -1.62
    )$
    -1.60
    POSITIVE LOGITS
    騭
    1.89
    歟
    1.88
    跻
    1.82
     perpé
    1.78
    ところに
    1.64
    $
    1.64
    ￪
    1.62
    you
    1.60
     dubious
    1.59
    情况下
    1.56
    Activations Density 0.005%

    No Known Activations