© 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-262K
    7. 149119
    Prev
    Next
    INDEX
    Explanations

    people or longer intervals

    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_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
    িন্ন
    0.81
    iley
    0.79
    ️
    0.79
    эль
    0.78
    oring
    0.78
    ily
    0.76
    или
    0.76
    ︎
    0.73
    їн
    0.73
    ersion
    0.73
    POSITIVE LOGITS
     individuals
    0.79
    人
    0.77
     indivíduos
    0.73
     जात
    0.72
    人的
    0.71
     individ
    0.68
     дій
    0.68
     people
    0.67
    সব
    0.67
     Individuals
    0.66
    Activations Density 0.001%

    No Known Activations