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-16K
    4. 271
    Prev
    Next
    INDEX
    Explanations

    names after separators

    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
    -
    0.55
     to
    0.54
     -
    0.54
     spp
    0.52
    ↵↵
    0.51
    .
    0.51
    :
    0.50
     속
    0.50
     for
    0.50
    ic
    0.49
    POSITIVE LOGITS
     Michael
    1.51
     John
    1.47
     Robert
    1.44
     Stephen
    1.41
     Richard
    1.41
     Patrick
    1.41
     William
    1.40
    Michael
    1.40
     Sarah
    1.40
     David
    1.40
    Activations Density 0.672%

    No Known Activations