© 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. 87614
    Prev
    Next
    INDEX
    Explanations

    helpful information or facts

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

    century, of, for, large, can

    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
     발생
    0.50
     Nationale
    0.48
    開封
    0.48
    ุณ
    0.48
     안정
    0.47
     Couleur
    0.47
    惯
    0.46
     복
    0.46
     ลูก
    0.46
     स्वभाव
    0.46
    POSITIVE LOGITS
     maps
    0.47
     lobbyists
    0.46
     informações
    0.45
     commissions
    0.45
     fares
    0.45
     treatises
    0.45
     coats
    0.44
     locations
    0.42
    ?“
    0.42
     bulb
    0.42
    Activations Density 0.002%

    No Known Activations