© 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. 143115
    Prev
    Next
    INDEX
    Explanations

    seen today, general manager

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

    multilingual words and concepts

    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
    :
    0.55
    1
    0.50
    response
    0.50
    หรือ
    0.50
    or
    0.49
     Marketing
    0.48
     Vehicle
    0.48
     Think
    0.47
    new
    0.47
     Options
    0.46
    POSITIVE LOGITS
    tdev
    0.53
     памя
    0.50
    ણને
    0.50
    쨩
    0.49
     bounces
    0.48
    ност
    0.47
    чиго
    0.47
     manipulator
    0.47
     saisons
    0.47
     creditor
    0.46
    Activations Density 0.001%

    No Known Activations