Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 14837
    Prev
    Next
    INDEX
    Explanations

    body parts and posture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     함수의
    1.16
     では
    1.15
     Where
    1.15
     定义
    1.14
     函数
    1.13
     Encyclopedia
    1.13
     要素
    1.13
     學
    1.11
    では
    1.10
     WHERE
    1.09
    POSITIVE LOGITS
    ties
    1.16
    atten
    1.07
    intim
    1.01
    ప్ప
    0.99
    nights
    0.94
    tsd
    0.93
    aff
    0.93
    neck
    0.92
    length
    0.90
    handed
    0.90
    Activations Density 0.021%

    No Known Activations