© 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. 34-GEMMASCOPE-RES-131K
    7. 73541
    Prev
    Next
    INDEX
    Explanations

    crackdown and aggravated crimes

    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
    preter
    -0.76
    CurrentValue
    -0.75
    ORTS
    -0.71
    kenen
    -0.71
    "><?
    -0.70
    gewä
    -0.68
    TRIGGER
    -0.67
    Reported
    -0.66
    economia
    -0.66
     Lighter
    -0.66
    POSITIVE LOGITS
     iaitu
    0.70
     became
    0.67
     Schloß
    0.67
     ceased
    0.63
     Oliva
    0.63
    ángulo
    0.62
     Marcia
    0.62
    発電
    0.61
     respects
    0.61
    discipl
    0.61
    Activations Density 0.067%

    No Known Activations