© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72476
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     Estudiantes
    -0.97
    際の
    -0.95
    際には
    -0.93
     Furthermore
    -0.92
    насе
    -0.92
    
    -0.91
     tradisi
    -0.91
    КП
    -0.90
     tendances
    -0.89
    弒
    -0.88
    POSITIVE LOGITS
    ttet
    0.96
    vedať
    0.88
    END
    0.83
    懲
    0.82
    频
    0.82
    orkan
    0.81
    Điều
    0.80
    Tại
    0.79
     harm
    0.79
     finally
    0.79
    Activations Density 0.005%

    No Known Activations