© 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. 123993
    Prev
    Next
    INDEX
    Explanations

    possession, Executive, Silicone

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

    enhancement request

    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
     сведения
    0.51
     сложные
    0.40
    ecimento
    0.40
     сложно
    0.40
    ნიშვნელ
    0.39
    lüssel
    0.39
    魟
    0.38
    குடும்ப
    0.38
    difficulty
    0.37
     сложности
    0.37
    POSITIVE LOGITS
     pouze
    0.54
     monetize
    0.50
     可愛い
    0.50
     ignores
    0.49
     tanpa
    0.49
    ！
    0.49
     ignore
    0.48
     spain
    0.48
     apenas
    0.47
     فقط
    0.46
    Activations Density 0.000%

    No Known Activations