© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12992
    Prev
    Next
    INDEX
    Explanations

    say "r" words

    np_max-act-logits · gemini-2.5-flash-lite
    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
    Resistance
    0.49
     Resistance
    0.45
    ওয়ে
    0.45
    羥
    0.45
     డౌ
    0.45
    ಂಟ
    0.44
    ويل
    0.44
    缪
    0.43
     diren
    0.43
    یدہ
    0.43
    POSITIVE LOGITS
     record
    5.88
    record
    5.69
     Record
    5.50
    Record
    5.44
     RECORD
    5.31
     records
    5.28
    RECORD
    5.13
    records
    5.00
     Records
    4.97
    记录
    4.97
    Activations Density 0.238%

    No Known Activations