© 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. 106934
    Prev
    Next
    INDEX
    Explanations

    what more or better

    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
    ли
    0.59
    хождения
    0.53
    <unused1>
    0.51
     атмосфер
    0.51
    网页
    0.50
    ంబేద్కర్
    0.50
     propriedades
    0.49
     особенности
    0.49
     کررہ
    0.48
     procédures
    0.48
    POSITIVE LOGITS
    ->
    0.66
    No
    0.66
    k
    0.66
    *,
    0.64
    WL
    0.61
    c
    0.57
    >,
    0.57
     l
    0.56
     *
    0.56
    Zn
    0.55
    Activations Density 0.000%

    No Known Activations