© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3549
    Prev
    Next
    INDEX
    Explanations

    HTML, code structure, list items, or options

    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
    𒌅
    0.68
    🈺
    0.68
    🕤
    0.67
    <unused1883>
    0.67
    <unused1862>
    0.67
    𒐪
    0.67
     فونبی
    0.66
    ⏮
    0.66
    <unused1953>
    0.65
    <unused1207>
    0.65
    POSITIVE LOGITS
    1
    0.72
    3
    0.62
    2
    0.55
    4
    0.55
    or
    0.54
    0.54
    .
    0.53
     III
    0.51
    8
    0.50
    7
    0.50
    Activations Density 0.000%

    No Known Activations