© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123824
    Prev
    Next
    INDEX
    Explanations

    crackdown on dissent

    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_10/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
     some
    -2.03
    "
    -1.84
     begle
    -1.71
     these
    -1.70
     this
    -1.66
     murió
    -1.66
    錚
    -1.66
     You
    -1.66
     many
    -1.65
    ⁛
    -1.65
    POSITIVE LOGITS
    Kamu
    1.86
     ekst
    1.84
     Ottobre
    1.82
    硨
    1.76
     modificare
    1.75
     maksimal
    1.73
    up
    1.72
     crackdown
    1.71
     truk
    1.71
     is
    1.71
    Activations Density 0.012%

    No Known Activations