© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1355
    Prev
    Next
    INDEX
    Explanations

    for individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
     Problem
    0.90
     While
    0.85
     Tension
    0.85
     Story
    0.84
     Moment
    0.81
    一
    0.77
     Directions
    0.77
     Once
    0.77
     Remains
    0.77
     Considering
    0.77
    POSITIVE LOGITS
     ヴィンテージ
    1.10
    <unused451>
    1.09
     warehouses
    1.09
     loafers
    1.09
    <unused447>
    1.08
    <unused443>
    1.07
    ꯣ
    1.06
    <unused237>
    1.06
    <unused448>
    1.05
    <unused294>
    1.05
    Activations Density 0.000%

    No Known Activations