© 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. 34-GEMMASCOPE-RES-131K
    7. 93413
    Prev
    Next
    INDEX
    Explanations

    quantities and ranges

    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_34/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
    Fair
    -0.89
     Fair
    -0.88
    maksi
    -0.87
    fair
    -0.85
     potencial
    -0.83
     Lem
    -0.81
    台北
    -0.81
    标准
    -0.80
    .'</
    -0.80
     fair
    -0.79
    POSITIVE LOGITS
     mấy
    1.14
     decenas
    1.13
     tens
    1.09
     dozens
    1.06
     кілька
    1.02
     hundreds
    1.00
     severa
    0.94
     vài
    0.93
    !?!
    0.89
     деся
    0.87
    Activations Density 0.028%

    No Known Activations