© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2908
    Prev
    Next
    INDEX
    Explanations

    trip from through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ћ
    0.73
    Ха
    0.73
     ұ
    0.72
     i
    0.71
     написа
    0.70
     цу
    0.70
     непотпу
    0.70
    кха
    0.70
    ђ
    0.70
     няма
    0.70
    POSITIVE LOGITS
     lahko
    1.31
     tudi
    1.30
     uporab
    1.29
     vedno
    1.27
     vse
    1.26
     nekaj
    1.25
     izdel
    1.24
     člove
    1.20
     brez
    1.18
     zelo
    1.17
    Activations Density 0.019%

    No Known Activations