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. 10
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and tags

    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
    stood
    0.63
    judicial
    0.61
     moieties
    0.60
    彳
    0.59
    chmod
    0.56
    granular
    0.56
    Trem
    0.55
    ilustración
    0.55
    legged
    0.55
    all
    0.54
    POSITIVE LOGITS
     class
    1.28
     style
    1.23
     Style
    1.08
     id
    1.08
     className
    1.05
    Style
    1.00
    ><
    1.00
    >&
    0.99
    style
    0.94
     estilo
    0.94
    Activations Density 0.270%

    No Known Activations