© 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. 27587
    Prev
    Next
    INDEX
    Explanations

    Days, months, names, abbreviations

    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
     in
    -1.22
    :
    -1.01
     sophisticated
    -0.96
     or
    -0.94
    Recently
    -0.87
     uniquely
    -0.86
     statusCode
    -0.86
    كاتب
    -0.85
     so
    -0.84
     with
    -0.83
    POSITIVE LOGITS
    izde
    1.16
     historiador
    1.05
     anderen
    0.98
    raktion
    0.97
    ཾ
    0.96
     $+
    0.95
    Ⓣ
    0.95
    פות
    0.95
     thậm
    0.92
    ellt
    0.91
    Activations Density 0.000%

    No Known Activations