© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8444
    Prev
    Next
    INDEX
    Explanations

    electrical charge and leaders

    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
    লাভ
    1.41
     naturelles
    1.32
     spectrom
    1.30
    
    1.29
     বেদ
    1.28
    র্জাতিক
    1.27
    이야
    1.26
     σχετικά
    1.26
    计量
    1.23
     oreilles
    1.23
    POSITIVE LOGITS
    ار
    1.30
    k
    1.27
    ্যাল
    1.24
    is
    1.20
    iknya
    1.16
    र
    1.10
    ik
    1.09
    сы
    1.09
    ч
    1.08
    ี
    1.07
    Activations Density 0.000%

    No Known Activations