© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14779
    Prev
    Next
    INDEX
    Explanations

    documentation parameters

    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_262k_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
     Gann
    0.76
     endors
    0.76
     reagents
    0.75
     Gan
    0.75
     car
    0.73
     আৰু
    0.72
    ,<
    0.72
     bàn
    0.72
     senate
    0.71
     participation
    0.71
    POSITIVE LOGITS
    Public
    0.79
    Priv
    0.79
    NOTE
    0.76
    public
    0.73
    চ্ছিলেন
    0.73
    Note
    0.73
    private
    0.72
    ({
    0.72
    Printer
    0.71
    Framework
    0.70
    Activations Density 0.001%

    No Known Activations