Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3653
    Prev
    Next
    INDEX
    Explanations

    NSRange for text

    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_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
     altro
    0.91
    ADOR
    0.88
    ईआरटी
    0.83
    $-$
    0.82
     ৩০০
    0.81
     atos
    0.79
     усилия
    0.76
     번째
    0.76
     vreme
    0.74
     molti
    0.72
    POSITIVE LOGITS
    ل
    1.35
    ು
    1.28
    r
    1.25
    n
    1.25
    ub
    1.22
    ay
    1.22
    uft
    1.21
    ight
    1.20
    in
    1.20
    عنی
    1.18
    Activations Density 0.289%

    No Known Activations