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. 149
    Prev
    Next
    INDEX
    Explanations

    strategy 1

    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
     (
    0.83
    ,
    0.61
    .
    0.60
     the
    0.59
     –
    0.58
    ↵↵
    0.58
     [
    0.57
      
    0.57
     specific
    0.55
     The
    0.55
    POSITIVE LOGITS
    Usuario
    0.91
    <unused2060>
    0.90
    Empleado
    0.87
    ogliamo
    0.87
    ཥ
    0.86
    <unused1984>
    0.85
    vaegir
    0.85
    binicons
    0.84
    atasaray
    0.84
    yní
    0.83
    Activations Density 4.125%

    No Known Activations