© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13409
    Prev
    Next
    INDEX
    Explanations

    assist with tasks

    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
     spéciaux
    1.48
    zec
    1.28
    对
    1.25
     peony
    1.24
    ចិត្ត
    1.24
     emissivity
    1.23
    teros
    1.22
    <bos>
    1.22
    hren
    1.21
    ද්ග
    1.20
    POSITIVE LOGITS
    ঘাত
    1.69
    Hallo
    1.63
     Build
    1.61
    ном
    1.58
    Й
    1.56
    staben
    1.53
    بود
    1.53
    Ш
    1.52
    paced
    1.52
    ҝ
    1.50
    Activations Density 0.092%

    No Known Activations