© 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. 76079
    Prev
    Next
    INDEX
    Explanations

    market, notice, per, six, such, support

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

    camera, magnitude, story, boyfriend, elastic, mapping

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aniach
    0.49
    acker
    0.46
     गोइंग
    0.46
    apad
    0.45
     preconceived
    0.45
    enton
    0.44
     ребенок
    0.44
    >[</
    0.43
     diaria
    0.42
    createElement
    0.42
    POSITIVE LOGITS
     Subsidi
    0.63
     DIF
    0.55
     IPTV
    0.49
    Ν
    0.48
    VAC
    0.47
     Distillery
    0.46
    Kü
    0.46
     subsidiaries
    0.46
     Waterfront
    0.45
    Ϲ
    0.45
    Activations Density 0.001%

    No Known Activations