© 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. 31-GEMMASCOPE-2-RES-262K
    7. 74548
    Prev
    Next
    INDEX
    Explanations

    verification of manual changes

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     embossing
    0.51
     linkages
    0.49
    اونلو
    0.48
     `./
    0.48
    πτυ
    0.48
     MODELS
    0.46
     vendre
    0.46
     optimised
    0.46
     OXIDES
    0.46
     Harga
    0.46
    POSITIVE LOGITS
    (
    0.48
    Av
    0.47
    at
    0.47
    Ex
    0.46
    大
    0.46
    见到
    0.46
    Maximum
    0.46
    ik
    0.45
    US
    0.44
    if
    0.43
    Activations Density 0.001%

    No Known Activations