© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10525
    Prev
    Next
    INDEX
    Explanations

    boot context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ోతి
    2.82
    oksatta
    2.51
    ﭥ
    2.40
    சையில்
    2.40
    <unused521>
    2.38
    aceis
    2.35
    িস্ট
    2.31
    轭
    2.28
    𒐸
    2.28
    学家
    2.28
    POSITIVE LOGITS
     opérés
    2.26
    res
    1.90
     .
    1.80
    resc
    1.73
     sprechen
    1.73
     ass
    1.72
    ছি
    1.71
    prising
    1.67
    𝒹
    1.67
    รือ
    1.66
    Activations Density 0.067%

    No Known Activations