© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 83391
    Prev
    Next
    INDEX
    Explanations

    character encoding, limits, and sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    字母
    0.54
     chữ
    0.52
     буквы
    0.47
    TA
    0.45
    澳
    0.42
    yya
    0.42
     حروف
    0.42
    σ
    0.41
     letras
    0.40
    identifier
    0.40
    POSITIVE LOGITS
    istically
    0.66
    itics
    0.61
    cter
    0.59
    ISTICS
    0.57
    istice
    0.56
    ization
    0.56
    ystycz
    0.55
    izer
    0.54
    istics
    0.53
    izations
    0.50
    Activations Density 0.021%

    No Known Activations