© 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. 2686
    Prev
    Next
    INDEX
    Explanations

    on ice

    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
     Campos
    0.75
     Kenya
    0.69
     Liberia
    0.66
     Ecuador
    0.66
     İran
    0.64
    Kenya
    0.64
     affirm
    0.63
    🏾
    0.63
     दलित
    0.63
     NAACP
    0.63
    POSITIVE LOGITS
     hockey
    2.19
     Hockey
    2.15
     skating
    2.11
    Hockey
    2.08
     NHL
    2.04
     puck
    2.02
     skate
    1.98
    hockey
    1.96
     skaters
    1.93
    NHL
    1.88
    Activations Density 0.192%

    No Known Activations