© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1094
    Prev
    Next
    INDEX
    Explanations

    game, technical, or descriptive text

    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
    Rise
    0.67
     stov
    0.66
    oxyd
    0.64
     Rise
    0.64
    консу
    0.63
     accept
    0.62
    號
    0.61
     φύ
    0.60
    ocks
    0.60
     Accidents
    0.60
    POSITIVE LOGITS
    Crazy
    0.53
     ving
    0.51
    tu
    0.51
     izan
    0.50
    ಬ್
    0.50
     Iterator
    0.50
    िड
    0.50
    ítani
    0.50
     বিগ
    0.50
    HashMap
    0.49
    Activations Density 0.251%

    No Known Activations