© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 19125
    Prev
    Next
    INDEX
    Explanations

    fractions and percentages like 1/4, 25%

    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
     avanti
    0.43
    ๘
    0.43
    १८४
    0.43
    憊
    0.43
    十八
    0.41
     जातो
    0.40
     १८४
    0.40
    ૯
    0.40
    ៨
    0.40
     ১৪
    0.39
    POSITIVE LOGITS
    ২৫
    1.10
     ২৫
    1.04
     २५
    1.03
     ৭৫
    1.01
     quarter
    0.87
     Quarter
    0.79
     XXV
    0.67
    Quarter
    0.66
     ¼
    0.65
    ¼
    0.65
    Activations Density 0.055%

    No Known Activations