© 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. 228287
    Prev
    Next
    INDEX
    Explanations

    food, professions, and religion

    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
    ਲਾ
    0.46
    ଲା
    0.44
    改變
    0.43
    𝚐
    0.43
    agreement
    0.42
    㳚
    0.42
     결과
    0.41
     зміню
    0.41
    ከት
    0.41
    elimin
    0.41
    POSITIVE LOGITS
     eğer
    0.52
     Strasbourg
    0.50
     Davos
    0.50
    0.49
    はもちろん
    0.48
     یا
    0.46
     Christophe
    0.46
     Beyoncé
    0.46
     Nuremberg
    0.45
     همچنین
    0.45
    Activations Density 0.002%

    No Known Activations