© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4659
    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_24_width_16k_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
    ানুভূতি
    0.90
    揸
    0.89
     moest
    0.88
     fundament
    0.87
     transmutation
    0.85
    ರುತ್ತ
    0.85
     mogen
    0.84
     voed
    0.84
     exorbit
    0.83
     berücksicht
    0.83
    POSITIVE LOGITS
    ש
    0.80
    ร
    0.71
     linee
    0.71
     when
    0.71
    い
    0.71
    מד
    0.69
    ן
    0.67
     ###
    0.66
     aspett
    0.63
    几十
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.