© 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. 70261
    Prev
    Next
    INDEX
    Explanations

    drastic, extreme, or impulsive action

    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
    offsetWidth
    -0.87
    вку
    -0.78
    TextWatcher
    -0.76
    ğını
    -0.75
     patate
    -0.73
    diz
    -0.72
    kiewicz
    -0.71
     léger
    -0.71
    andar
    -0.71
     कर
    -0.71
    POSITIVE LOGITS
     drastic
    3.88
     extreme
    3.31
    extreme
    2.89
    dras
    2.66
    Extreme
    2.63
     desperate
    2.36
     Extreme
    2.36
     radical
    2.31
     dras
    2.30
     край
    2.28
    Activations Density 0.070%

    No Known Activations