© 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. 3124
    Prev
    Next
    INDEX
    Explanations

    region in space

    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
    prev
    0.93
     pourcentage
    0.87
     precedes
    0.86
     exceeds
    0.85
     allows
    0.80
     includes
    0.80
    𓍊
    0.78
     எரி
    0.77
     enables
    0.76
    iž
    0.76
    POSITIVE LOGITS
    if
    0.78
    Lab
    0.78
    <bos>
    0.74
     elif
    0.72
     mało
    0.72
    ถ้า
    0.71
     kalau
    0.69
    when
    0.69
    Khi
    0.68
    If
    0.68
    Activations Density 0.002%

    No Known Activations