© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8231
    Prev
    Next
    INDEX
    Explanations

    turn off, turn out, turn into

    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_13_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
    offsetHeight
    1.51
    ed
    1.50
    संख्यक
    1.49
    त
    1.47
    sites
    1.43
    珅
    1.42
    <bos>
    1.42
     ہاتھوں
    1.42
    ໊
    1.39
    程度の
    1.35
    POSITIVE LOGITS
     rápid
    1.58
    ্টে
    1.45
    тика
    1.45
    ্বিত
    1.44
    pike
    1.44
    stile
    1.42
     converter
    1.41
    ikale
    1.40
     الجم
    1.38
    งาน
    1.38
    Activations Density 0.328%

    No Known Activations