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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7364
    Prev
    Next
    INDEX
    Explanations

    system braking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
    и
    1.03
    cciona
    1.03
    iriya
    1.03
    சில்
    1.01
    а
    1.00
     bona
    0.99
    GULD
    0.99
    нга
    0.99
     sujet
    0.98
     concl
    0.98
    POSITIVE LOGITS
    kę
    1.17
    executionContext
    1.16
    yaw
    1.12
    Osc
    1.12
    ꞌ
    1.12
     puffs
    1.11
    課程
    1.10
     −
    1.10
    值
    1.10
    ucers
    1.10
    Activations Density 0.000%

    No Known Activations