© 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. 90506
    Prev
    Next
    INDEX
    Explanations

    custom ROMs

    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
    槑
    0.50
     Asst
    0.49
    旖
    0.49
    Các
    0.48
     NXT
    0.48
     NADH
    0.48
    हाल
    0.47
     Plante
    0.47
     Poch
    0.47
    <h4>
    0.46
    POSITIVE LOGITS
    ;#
    0.57
    ;
    0.52
     tup
    0.50
     கொ
    0.50
     cei
    0.49
    ]
    0.49
    )$
    0.49
    re
    0.48
     invitados
    0.48
     harvest
    0.48
    Activations Density 0.000%

    No Known Activations