© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36396
    Prev
    Next
    INDEX
    Explanations

    import or testing library

    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
     data
    -1.05
     If
    -1.01
     Throughout
    -0.96
     distinctly
    -0.95
     will
    -0.92
    issantes
    -0.86
    ၅
    -0.85
     ((
    -0.85
     Unlike
    -0.83
     Gesellschaft
    -0.83
    POSITIVE LOGITS
    Poz
    1.06
    STAY
    1.05
    cij
    0.96
     GLAD
    0.96
    sont
    0.95
     ELE
    0.95
    ghton
    0.94
     قرن
    0.93
    ほとん
    0.92
    Hosp
    0.92
    Activations Density 0.001%

    No Known Activations