© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1131
    Prev
    Next
    INDEX
    Explanations

    start every prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    -”
    0.71
    mination
    0.69
    .’
    0.68
     samos
    0.66
    <unused849>
    0.65
     electroph
    0.65
    .”
    0.64
     arguing
    0.63
    婍
    0.63
    。”
    0.62
    POSITIVE LOGITS
     tutte
    0.66
     всички
    0.63
    ו
    0.57
    ுகள்
    0.56
    สิ่ง
    0.55
     усі
    0.55
    Inserted
    0.54
     Job
    0.53
    வுகள்
    0.53
    น
    0.53
    Activations Density 0.006%

    No Known Activations