© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8077
    Prev
    Next
    INDEX
    Explanations

    monetary values

    np_acts-logits-general · gemini-2.5-flash-lite

    prices and amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    億
    0.33
     milij
    0.31
    ﾕ
    0.29
     настоящий
    0.29
     billion
    0.28
     milli
    0.28
     میلی
    0.28
    ANAL
    0.28
     миллиар
    0.28
    ♂
    0.28
    POSITIVE LOGITS
    oma
    0.30
    ack
    0.30
     addiction
    0.30
     昨日
    0.29
    gawa
    0.29
    ato
    0.29
     volunteers
    0.28
    ait
    0.28
    iao
    0.28
    ojn
    0.28
    Activations Density 0.051%

    No Known Activations