© 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. 34595
    Prev
    Next
    INDEX
    Explanations

    specific names and types

    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
     his
    -1.16
     jego
    -0.99
     another
    -0.97
     его
    -0.95
     яго
    -0.86
     másik
    -0.84
     seiner
    -0.84
    بیل
    -0.82
    תו
    -0.81
     другой
    -0.81
    POSITIVE LOGITS
    Phew
    0.92
    Geograf
    0.90
    Также
    0.82
     ihrem
    0.81
    StringVar
    0.80
     statis
    0.78
    Далее
    0.78
     män
    0.77
     इसका
    0.77
     Assyrian
    0.77
    Activations Density 0.489%

    No Known Activations