© 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. 15478
    Prev
    Next
    INDEX
    Explanations

    say "prompt"

    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
    ဝ်
    0.58
    astere
    0.52
    oso
    0.51
    研
    0.51
    芜
    0.51
    كيل
    0.49
    gdx
    0.49
    討
    0.49
    诚
    0.49
    iedz
    0.48
    POSITIVE LOGITS
     promotion
    5.06
    Prom
    4.97
     Promotion
    4.88
     Prom
    4.84
    prom
    4.81
     prom
    4.78
    Promotion
    4.78
     promoted
    4.72
    promotion
    4.69
     promote
    4.66
    Activations Density 0.187%

    No Known Activations