© 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. 22-GEMMASCOPE-2-RES-262K
    4. 14808
    Prev
    Next
    INDEX
    Explanations

    medical reasons or report

    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_22_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
     leta
    0.69
     gimm
    0.67
     $)
    0.61
    ठमाड
    0.61
     
    0.60
    殺
    0.59
    ক্ষেপ
    0.58
     wiss
    0.58
    ?",
    0.58
     inducement
    0.57
    POSITIVE LOGITS
    viation
    0.78
    ya
    0.74
    nya
    0.73
    nin
    0.69
    able
    0.66
    mol
    0.65
    nine
    0.64
    ck
    0.64
    n
    0.64
    soccer
    0.63
    Activations Density 0.000%

    No Known Activations