© 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. 91013
    Prev
    Next
    INDEX
    Explanations

    state of

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

    specific locations and events

    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
     corps
    0.45
    許多
    0.45
     夕
    0.45
     пользователя
    0.44
     党
    0.44
    十二
    0.43
     三
    0.43
     narcot
    0.43
     八
    0.42
     魔
    0.42
    POSITIVE LOGITS
    ভাসের
    0.47
     olduğu
    0.44
     journeys
    0.44
     Almanya
    0.44
    ان
    0.42
     Zeitraum
    0.41
     Andover
    0.41
    弑
    0.41
    ঙ্গের
    0.40
     Dementia
    0.40
    Activations Density 0.000%

    No Known Activations