© 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. 149084
    Prev
    Next
    INDEX
    Explanations

    county and location names

    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
     Ves
    0.82
    െയ്
    0.77
     Tandy
    0.74
     Tenn
    0.73
    orgung
    0.72
    ቮ
    0.70
     Anh
    0.68
    Tesla
    0.68
     টে
    0.67
    टीआई
    0.67
    POSITIVE LOGITS
     county
    0.74
     FUN
    0.72
     fung
    0.71
     functional
    0.69
    ંબ
    0.69
     funk
    0.69
    珲
    0.69
    FUNCTION
    0.69
    Functional
    0.68
     FUNCTION
    0.68
    Activations Density 0.001%

    No Known Activations