© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 6080
    Prev
    Next
    INDEX
    Explanations

    greetings and welcomes

    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
    かかる
    0.56
     intrinsic
    0.56
     worst
    0.55
    excluding
    0.55
    :
    0.54
     downg
    0.54
     breakage
    0.53
    ಶಸ್
    0.52
    emorrh
    0.50
     attack
    0.50
    POSITIVE LOGITS
     👋
    1.87
     greetings
    1.73
     welkom
    1.69
     welcome
    1.68
     Welcome
    1.65
    👋
    1.64
     bienvenue
    1.58
    欢迎
    1.55
     Greetings
    1.54
    Welcome
    1.53
    Activations Density 0.258%

    No Known Activations