© 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. 34-GEMMASCOPE-RES-131K
    7. 1518
    Prev
    Next
    INDEX
    Explanations

    c- followed by word

    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
    mcc
    -0.91
    iertas
    -0.86
     Krzysz
    -0.85
    jà
    -0.85
    ườ
    -0.85
     others
    -0.80
    jalan
    -0.80
     Максима
    -0.79
     juridique
    -0.79
     Worry
    -0.79
    POSITIVE LOGITS
     c
    1.54
    ̓
    0.86
    ｃ
    0.85
    χος
    0.85
     тем
    0.84
    ¢
    0.81
    ③
    0.79
    ⅅ
    0.79
    c
    0.79
     piment
    0.79
    Activations Density 0.052%

    No Known Activations