© 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. 248178
    Prev
    Next
    INDEX
    Explanations

    group training

    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
     are
    0.47
     v
    0.46
     yas
    0.46
     padx
    0.45
    s
    0.45
     a
    0.44
     s
    0.43
     reward
    0.42
    с
    0.42
     expired
    0.42
    POSITIVE LOGITS
    텐츠
    0.52
     Сим
    0.50
     Кі
    0.49
     सेल्स
    0.49
     Killing
    0.48
     RSC
    0.48
    ustain
    0.46
     Київ
    0.46
     इश्क
    0.46
    竅
    0.45
    Activations Density 0.000%

    No Known Activations