© 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. 15790
    Prev
    Next
    INDEX
    Explanations

    literally / translation

    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
    ıll
    0.63
    $}
    0.60
     NÃO
    0.56
     ensures
    0.55
    无效
    0.55
    ্লাই
    0.54
    时不
    0.54
    मेंट्स
    0.53
    ೫
    0.53
     ব্যাবহার
    0.52
    POSITIVE LOGITS
     literally
    1.79
    literally
    1.78
     Literally
    1.75
     literalmente
    1.70
     буквально
    1.37
     literal
    1.23
     بمعنى
    1.17
    literal
    1.16
     Literal
    1.16
    roughly
    1.16
    Activations Density 0.064%

    No Known Activations