© 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. 113952
    Prev
    Next
    INDEX
    Explanations

    landing site

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

    fulfilling requirements

    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
    鳎
    0.66
    珽
    0.53
    魟
    0.53
    齙
    0.52
    㚘
    0.52
     мыкты
    0.51
    桉
    0.50
     খবর
    0.50
     बातम्या
    0.50
    鲟
    0.49
    POSITIVE LOGITS
     "
    0.55
     ("
    0.52
    s
    0.49
     "(
    0.49
     ".
    0.47
     _
    0.47
     ,
    0.47
     Liu
    0.47
     amid
    0.46
    x
    0.46
    Activations Density 0.002%

    No Known Activations