© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189945
    Prev
    Next
    INDEX
    Explanations

    lists of specific entities

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

    measure understanding

    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
     Spray
    0.55
     Beach
    0.55
     is
    0.54
    ↵↵
    0.53
     v
    0.53
      
    0.52
    ot
    0.51
    </b>
    0.50
    on
    0.50
     (
    0.50
    POSITIVE LOGITS
     Министерства
    0.63
    pulsewidth
    0.59
    ヤモンド
    0.59
     mostrou
    0.57
    ложи
    0.57
     lLoginID
    0.55
     diminue
    0.54
     mediados
    0.51
     meriye
    0.51
     samoglas
    0.50
    Activations Density 0.001%

    No Known Activations