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. 22-GEMMASCOPE-2-RES-16K
    4. 736
    Prev
    Next
    INDEX
    Explanations

    people's names

    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_16k_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
    $$
    0.41
     
    0.40
     a
    0.39
     the
    0.38
     =
    0.38
     (
    0.37
    Mr
    0.36
    proof
    0.36
    (
    0.35
    :
    0.34
    POSITIVE LOGITS
     anthropologist
    0.64
     modalCard
    0.60
    ércio
    0.60
     cGraph
    0.59
     cognitiva
    0.58
     livro
    0.58
    𐰴
    0.58
     anthropologists
    0.58
     neoliberal
    0.57
    漃
    0.57
    Activations Density 0.179%

    No Known Activations