Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1110
    Prev
    Next
    INDEX
    Explanations

    call oflongevity ofrise ofinfluence ofdepletion offlow ofreview ofscalability ofRole of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    ™.
    1.05
     çünkü
    1.04
     ហើយ
    1.03
    .;
    1.01
    ।
    0.99
    ؛
    0.98
     karena
    0.96
     whereas
    0.94
    ។
    0.94
    ₁.
    0.92
    POSITIVE LOGITS
    CT
    0.53
    таль
    0.49
    ீர
    0.48
    io
    0.48
    card
    0.47
    任意
    0.46
    ending
    0.46
    ITATION
    0.44
    itation
    0.43
    ഴു
    0.43
    Activations Density 0.887%

    No Known Activations