© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 117256
    Prev
    Next
    INDEX
    Explanations

    quotes or names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    <0x0D>
    0.59
    𝘦
    0.58
    𝘪
    0.55
    ojen
    0.54
     verhindern
    0.52
    arı
    0.52
    ände
    0.52
    𝘰
    0.52
    ){
    0.51
    utis
    0.51
    POSITIVE LOGITS
     oscillators
    0.55
    نا
    0.55
    ყენ
    0.54
    ها
    0.53
    ν
    0.53
    ն
    0.53
     ዓይ
    0.52
     Tú
    0.52
    ンプル
    0.52
     Bowers
    0.52
    Activations Density 0.000%

    No Known Activations