© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 171893
    Prev
    Next
    INDEX
    Explanations

    documentary, illustration, Domain, maximal, vs

    np_acts-logits-general · gemini-2.5-flash-lite

    generating novel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ü
    0.53
     Font
    0.52
     Souls
    0.48
     Ü
    0.46
     n
    0.46
     Ú
    0.46
    ii
    0.45
     gegründet
    0.45
    ٻ
    0.44
     aktu
    0.44
    POSITIVE LOGITS
    SendData
    0.51
    したが
    0.51
     শান্তি
    0.49
    вшего
    0.49
    рино
    0.49
    лина
    0.48
    peace
    0.48
    穏
    0.48
    chin
    0.47
    蚕
    0.47
    Activations Density 0.000%

    No Known Activations