© 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. 195259
    Prev
    Next
    INDEX
    Explanations

    sync, team, screen, destroy

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

    access Ratio Freedom Design

    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
    noDB
    0.47
    গ্রস্ত
    0.47
    境界層
    0.46
    攘
    0.46
    凶
    0.46
    ೋಗ
    0.46
     தச
    0.46
    rocessing
    0.45
    簡単な
    0.44
    ERRE
    0.44
    POSITIVE LOGITS
    ↵
    0.52
     associée
    0.49
     demonstrate
    0.48
     salons
    0.48
     quyền
    0.47
     trat
    0.47
     frosts
    0.47
     appels
    0.47
     opérations
    0.47
     网
    0.47
    Activations Density 0.002%

    No Known Activations