© 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. 10325
    Prev
    Next
    INDEX
    Explanations

    values and numbers in formulas

    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
    т
    1.12
    у
    1.12
    и
    1.09
    НИЕ
    1.01
    ница
    0.99
     거라고
    0.98
    хой
    0.96
     opinion
    0.95
    я
    0.94
    ૂર
    0.93
    POSITIVE LOGITS
    bau
    1.27
    venv
    1.26
    ss
    1.20
    colours
    1.17
    vens
    1.15
    vector
    1.15
    lož
    1.14
    pojo
    1.13
    vegetarian
    1.13
    geo
    1.13
    Activations Density 0.003%

    No Known Activations