© 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. 190783
    Prev
    Next
    INDEX
    Explanations

    in a or at times

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

    is commonly particularly

    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
    atani
    0.55
    alem
    0.52
    arrow
    0.50
     row
    0.49
     column
    0.49
    at
    0.48
    려
    0.48
    czy
    0.47
     wiped
    0.47
          
    0.47
    POSITIVE LOGITS
    兩種
    0.52
    ئر
    0.47
    两种
    0.47
    ير
    0.46
    传统的
    0.46
     siècles
    0.46
    гули
    0.46
    屢
    0.46
    ائنات
    0.45
    社会
    0.44
    Activations Density 0.001%

    No Known Activations