© 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. 16251
    Prev
    Next
    INDEX
    Explanations

    apologies for delay or confusion

    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
    ibilité
    0.77
     nowych
    0.70
    ير
    0.68
    Cm
    0.67
    지
    0.64
     новых
    0.63
    9
    0.61
    ד
    0.61
     aprire
    0.61
    ٹا
    0.60
    POSITIVE LOGITS
    1.03
    t
    0.71
    ens
    0.61
    elen
    0.60
    itel
    0.60
     ਨਾਲ
    0.59
    ák
    0.57
    rapes
    0.57
     t
    0.55
     punt
    0.55
    Activations Density 0.009%

    No Known Activations