© 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. 34-GEMMASCOPE-RES-131K
    4. 98800
    Prev
    Next
    INDEX
    Explanations

    musician and band names

    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
     attentive
    -0.77
     enterprise
    -0.76
    dancer
    -0.73
    ︻
    -0.70
    Autonomous
    -0.70
    antiate
    -0.70
    NSFW
    -0.68
     Weston
    -0.68
     άλ
    -0.67
    anthem
    -0.67
    POSITIVE LOGITS
     Stavanger
    0.85
    alamus
    0.84
    ENCED
    0.81
     boomers
    0.79
    RESET
    0.76
     DRS
    0.73
    anga
    0.73
     Placebo
    0.72
    size
    0.72
    rese
    0.71
    Activations Density 0.075%

    No Known Activations