© 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. 2292
    Prev
    Next
    INDEX
    Explanations

    years, dates, ordinals

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

    numbers and dates

    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
     हाथों
    0.35
     Toán
    0.35
    ının
    0.33
    ücke
    0.33
     trustworthiness
    0.32
    闶
    0.32
    гнозы
    0.32
    かれた
    0.32
    廾
    0.32
    蓴
    0.32
    POSITIVE LOGITS
    years
    0.55
    th
    0.54
    year
    0.50
    9
    0.50
    8
    0.49
    0
    0.48
    rst
    0.48
    7
    0.46
    rd
    0.45
    5
    0.44
    Activations Density 0.340%

    No Known Activations