© 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. 183443
    Prev
    Next
    INDEX
    Explanations

    Norwegian conclusion purchases

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

    AI agents, game mechanics, text filling

    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
     ém
    0.52
     見
    0.50
     ɛ
    0.49
    ん
    0.48
    plate
    0.48
     таблицы
    0.46
    娓
    0.44
    kill
    0.43
     ř
    0.43
    शीलता
    0.43
    POSITIVE LOGITS
    OGRAP
    0.49
    পন্থ
    0.47
     sponsorships
    0.47
    ut
    0.46
     autographs
    0.46
    ARIFF
    0.46
     toppings
    0.45
     comforts
    0.44
     heaviest
    0.44
     laund
    0.43
    Activations Density 0.001%

    No Known Activations