© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32805
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    list followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    кро
    0.48
    ,
    0.46
    ه
    0.46
    қ
    0.45
     •
    0.44
    تان
    0.44
    <0x80>
    0.44
    lock
    0.44
    ructions
    0.44
    дни
    0.43
    POSITIVE LOGITS
    녠
    0.54
    لڈ
    0.50
    आईपी
    0.50
    矩阵
    0.49
    博客
    0.48
     matrice
    0.48
     stadium
    0.47
     hindu
    0.47
    ্লিষ্ট
    0.47
     estadio
    0.46
    Activations Density 0.000%

    No Known Activations