© 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. 90679
    Prev
    Next
    INDEX
    Explanations

    names preceded by quotes

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

    speech reporting verbs

    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
    社會
    0.49
     داده
    0.48
    SYSTEM
    0.43
     communities
    0.41
    研
    0.41
     publication
    0.41
    社
    0.41
    蓝
    0.41
    論文
    0.40
    क्षम
    0.40
    POSITIVE LOGITS
    knie
    0.43
    ņi
    0.42
     เอา
    0.41
     grinned
    0.41
     ጥሩ
    0.41
     দুর্দান্ত
    0.41
    пион
    0.41
     Estadio
    0.40
    mouse
    0.40
    ermis
    0.40
    Activations Density 0.011%

    No Known Activations