© 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. 76083
    Prev
    Next
    INDEX
    Explanations

    don't want to

    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
     défauts
    -1.04
    instead
    -0.98
     bättre
    -0.97
     appétit
    -0.96
    amkeit
    -0.95
     ingrédients
    -0.93
    somewhat
    -0.93
    VIR
    -0.91
     somewhat
    -0.91
    доби
    -0.91
    POSITIVE LOGITS
     risk
    1.88
     even
    1.73
     risking
    1.43
    risk
    1.42
     risks
    1.34
     risked
    1.32
    Even
    1.27
     Risk
    1.24
     rush
    1.23
     until
    1.21
    Activations Density 0.033%

    No Known Activations