© 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. 17-GEMMASCOPE-2-RES-16K
    7. 9205
    Prev
    Next
    INDEX
    Explanations

    function documentation strings

    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_17_width_16k_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
    ómico
    1.15
     pédicule
    1.15
    ávají
    1.11
     проходит
    1.11
    ípio
    1.09
    ქვს
    1.09
    鉐
    1.08
     متحده
    1.08
     доступа
    1.08
     pérd
    1.08
    POSITIVE LOGITS
    ve
    1.04
     gru
    1.01
     Trivia
    0.93
     slanted
    0.90
     glory
    0.90
     p
    0.90
     craz
    0.87
     playful
    0.87
    0.87
     l
    0.86
    Activations Density 0.051%

    No Known Activations