© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14043
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Balloon
    0.64
    ्लादेश
    0.59
    diox
    0.57
    <thead>
    0.54
    ⚋
    0.54
    Shuffle
    0.52
    Sodium
    0.51
    食用
    0.51
    balloon
    0.50
    Sentiment
    0.50
    POSITIVE LOGITS
     supporting
    0.65
     dental
    0.60
     servicing
    0.58
     stip
    0.56
     cite
    0.55
     M
    0.55
     Discovery
    0.55
     BL
    0.54
     close
    0.53
     Ferr
    0.53
    Activations Density 0.000%

    No Known Activations