© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 145429
    Prev
    Next
    INDEX
    Explanations

    metal, devices, jacket, contract

    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
    Negative Logits
     only
    0.59
     became
    0.55
    ن
    0.55
    Only
    0.55
     jää
    0.52
     gather
    0.52
    n
    0.52
    Location
    0.51
    ONLY
    0.50
     సం
    0.50
    POSITIVE LOGITS
     UNIVERS
    0.55
    です
    0.47
     ناول
    0.46
    ᡧ
    0.46
     prestig
    0.46
    retti
    0.46
    esty
    0.44
     noved
    0.43
    cla
    0.43
    助手
    0.43
    Activations Density 0.000%

    No Known Activations