© 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. 29-GEMMASCOPE-2-RES-65K
    7. 5194
    Prev
    Next
    INDEX
    Explanations

    goosebumps

    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_29_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
    國民
    0.72
     FOUR
    0.68
     ch
    0.67
    pe
    0.66
    语言
    0.65
     Four
    0.65
     Pe
    0.64
     퍼
    0.64
    Four
    0.63
    Pe
    0.63
    POSITIVE LOGITS
    BU
    0.69
     BU
    0.68
    Bu
    0.66
    Lets
    0.65
    ВА
    0.65
     Bu
    0.64
    хову
    0.64
    бу
    0.64
    hkse
    0.62
     fnt
    0.61
    Activations Density 0.202%

    No Known Activations