© 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. 13176
    Prev
    Next
    INDEX
    Explanations

    Radio Frequency abbreviation

    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
    {
    -3.78
     a
    -2.44
     With
    -2.41
    $
    -2.34
    ."
    -2.27
     или
    -2.19
     */
    -2.16
    ].
    -2.08
     laquelle
    -2.06
    .
    -2.00
    POSITIVE LOGITS
    趼
    3.56
     après
    2.72
    蚰
    2.69
    ية
    2.50
    唬
    2.48
     Perſ
    2.42
    荽
    2.39
     femeninos
    2.33
    ︕
    2.33
     ſeveral
    2.31
    Activations Density 0.004%

    No Known Activations