© 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. 43925
    Prev
    Next
    INDEX
    Explanations

    information, or how-to guides

    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
    сон
    0.62
    Ր
    0.60
     öffentliche
    0.59
    ᅣ
    0.59
    卢
    0.56
    라마
    0.55
    Ⲕ
    0.55
    Ꮼ
    0.54
    쐞
    0.54
     ancienne
    0.53
    POSITIVE LOGITS
    ile
    0.57
    eter
    0.55
    rip
    0.55
    ’
    0.55
    s
    0.54
     &
    0.53
    org
    0.52
    pa
    0.52
     in
    0.50
    ied
    0.50
    Activations Density 0.000%

    No Known Activations