© 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. 141329
    Prev
    Next
    INDEX
    Explanations

    suit your needs

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

    don't overdo

    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
    Negative Logits
    Fy
    0.50
    Fif
    0.49
    Trajectory
    0.45
    >∕</
    0.45
    ate
    0.45
     trajectory
    0.45
    Happ
    0.43
     +-
    0.43
     roadside
    0.42
    }{}
    0.42
    POSITIVE LOGITS
    बच्चों
    0.55
    蔭
    0.53
    кли
    0.52
    豪華
    0.52
     Ř
    0.52
    イス
    0.52
    ности
    0.50
     अवसर
    0.50
     Außen
    0.49
    ボリューム
    0.49
    Activations Density 0.000%

    No Known Activations