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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14970
    Prev
    Next
    INDEX
    Explanations

    birthday

    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
    ͖
    0.56
     अवलंब
    0.54
    ទេស
    0.49
     intermediary
    0.48
     Flüss
    0.48
    ਔ
    0.48
     petani
    0.48
    PreferredItem
    0.47
    intermedi
    0.47
    ({},
    0.47
    POSITIVE LOGITS
     birthday
    4.69
     Birthday
    4.44
    birthday
    4.28
    Birthday
    4.22
     birthdays
    4.09
    生日
    3.78
     जन्मदिन
    3.69
     cumpleaños
    3.63
     बर्थडे
    3.52
    誕生日
    3.52
    Activations Density 0.102%

    No Known Activations