© 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. 15667
    Prev
    Next
    INDEX
    Explanations

    transition 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
     Kochubei
    0.70
     ‏
    0.67
     ‫
    0.66
     mavenCentral
    0.66
     soorten
    0.65
     ."
    0.65
     onders
    0.65
     justifyContent
    0.64
     awọn
    0.64
     manhã
    0.64
    POSITIVE LOGITS
    Anyway
    0.78
    Lastly
    0.77
    Nonetheless
    0.76
    alas
    0.73
    IMO
    0.73
    ________________
    0.72
    Nevertheless
    0.72
    Moreover
    0.71
    EDIT
    0.71
    Anyways
    0.71
    Activations Density 0.000%

    No Known Activations