© 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. 159656
    Prev
    Next
    INDEX
    Explanations

    world in

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

    when faced with conditions

    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
    <bbox>
    0.48
     defocused
    0.48
    ходил
    0.48
     velké
    0.48
     داله
    0.46
     আব্দ
    0.46
     الصفحه
    0.46
    филь
    0.46
     ए
    0.46
    រួ
    0.45
    POSITIVE LOGITS
     Association
    0.47
     Tobacco
    0.46
     songs
    0.46
     Principal
    0.45
     Retail
    0.45
    ollar
    0.45
    ât
    0.44
     it
    0.43
     ROOT
    0.43
     OEM
    0.43
    Activations Density 0.001%

    No Known Activations