© 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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 269
    Prev
    Next
    INDEX
    Explanations

    music, economic, math discussions

    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
    Counters
    1.00
     Honestly
    0.93
    кат
    0.91
    ز
    0.89
     Observations
    0.89
    鑊
    0.86
     Shelf
    0.86
    鉤
    0.84
    แค
    0.84
    রে
    0.83
    POSITIVE LOGITS
     کولو
    0.76
    主管部门
    0.75
    ൦
    0.74
     edible
    0.74
     encycl
    0.72
     educa
    0.70
     dept
    0.69
    ামুটি
    0.69
    面
    0.68
    镂
    0.68
    Activations Density 0.371%

    No Known Activations