© 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. 149017
    Prev
    Next
    INDEX
    Explanations

    German cities and regions

    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
     marine
    0.92
     coastal
    0.90
     Jamestown
    0.85
     surfing
    0.84
     INDUSTR
    0.83
     ዳ
    0.83
     maritime
    0.83
    Marine
    0.80
     seamen
    0.79
     surf
    0.79
    POSITIVE LOGITS
     doctrinal
    0.70
     Schnee
    0.69
     Broom
    0.67
     plaf
    0.67
    ियस
    0.66
     Neb
    0.65
     Stras
    0.65
     ceiling
    0.64
     Vienna
    0.64
    琼
    0.64
    Activations Density 0.002%

    No Known Activations