© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93160
    Prev
    Next
    INDEX
    Explanations

    independent, primary, radio, search

    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
     to
    -1.23
     or
    -1.18
     having
    -1.09
     If
    -1.07
     so
    -1.04
     being
    -1.04
     There
    -1.00
     if
    -0.98
     with
    -0.98
    我国
    -0.97
    POSITIVE LOGITS
     sämtliche
    1.03
     aparcamiento
    0.93
    cist
    0.92
     هول
    0.91
     BERNARD
    0.91
    entire
    0.90
     curs
    0.89
    鶫
    0.88
     اوم
    0.88
    ouille
    0.88
    Activations Density 0.005%

    No Known Activations