© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    numbers, quantities, measurements

    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
    鷳
    0.43
    াষ
    0.35
    ጆች
    0.35
    ראל
    0.34
     اہمیت
    0.34
     বলে
    0.33
     важли
    0.33
    েন্টের
    0.33
    䄱
    0.33
     advocates
    0.33
    POSITIVE LOGITS
    5
    0.63
    0
    0.52
    2
    0.52
    3
    0.52
    jpg
    0.51
    4
    0.50
    6
    0.50
    9
    0.50
    8
    0.50
    1
    0.49
    Activations Density 0.332%

    No Known Activations