© 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. 2874
    Prev
    Next
    INDEX
    Explanations

    right now

    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
    দশ
    0.69
    彊
    0.67
    élim
    0.63
     인터
    0.62
     Inter
    0.60
    cluse
    0.60
     plain
    0.58
    overline
    0.57
    दशी
    0.57
     ausz
    0.56
    POSITIVE LOGITS
     ли
    0.66
     ल
    0.64
    PEC
    0.64
    wa
    0.63
    リ
    0.61
    node
    0.60
     სიმ
    0.59
     Sot
    0.58
    pec
    0.58
    ww
    0.57
    Activations Density 0.159%

    No Known Activations