© 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. 43099
    Prev
    Next
    INDEX
    Explanations

    new entity or configuration

    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
     $^{\
    -2.20
    㐂
    -2.13
     leichte
    -2.11
    }
    -2.09
     $^{
    -2.03
     but
    -1.96
     in
    -1.91
     "];
    -1.91
     spezielle
    -1.90
     höhere
    -1.88
    POSITIVE LOGITS
    New
    2.34
    If
    2.22
     coute
    2.09
    ’
    2.03
     unſ
    2.03
    小孩子
    2.02
    \
    2.02
    豋
    1.98
    >
    1.97
     первой
    1.96
    Activations Density 0.010%

    No Known Activations