© 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. 589
    Prev
    Next
    INDEX
    Explanations

    reach out for help

    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
    ar
    0.91
    ानों
    0.91
    에
    0.86
     bad
    0.82
     task
    0.80
     dog
    0.80
    صميم
    0.79
     career
    0.75
    그리고
    0.75
     line
    0.74
    POSITIVE LOGITS
     fruition
    1.07
     अबाउट
    1.05
    বিস্তারিত
    1.04
    ୍ୟ
    1.02
    ➖➖
    1.01
    ោក
    1.01
    <unused577>
    1.00
     ಗಳ
    1.00
    <unused669>
    1.00
     promot
    0.99
    Activations Density 0.201%

    No Known Activations