© 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. 79186
    Prev
    Next
    INDEX
    Explanations

    perfect blacks

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

    hierarchical classification

    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
    ائش
    0.54
    ర్యా
    0.47
    ämm
    0.47
     campaigned
    0.46
    蜃
    0.44
    形成了
    0.44
    球面
    0.44
    ائض
    0.44
    hasClass
    0.43
    цер
    0.43
    POSITIVE LOGITS
    u
    0.50
    skill
    0.49
     Studio
    0.48
    el
    0.47
     de
    0.47
     Skill
    0.46
    paste
    0.46
    🥋
    0.45
     por
    0.44
    speeds
    0.44
    Activations Density 0.000%

    No Known Activations