© 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. 9714
    Prev
    Next
    INDEX
    Explanations

    final results

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

    testing factory logic

    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
    world
    0.55
    մ
    0.52
    that
    0.50
    ku
    0.47
    wash
    0.47
    star
    0.46
    産業
    0.46
    मह
    0.45
    sey
    0.45
    mesh
    0.45
    POSITIVE LOGITS
     숫
    0.50
     പറയാ
    0.48
     ডা
    0.48
     Nummer
    0.47
     Mathematik
    0.46
     montré
    0.46
     方法
    0.46
     numar
    0.46
     satir
    0.45
     Mathematics
    0.44
    Activations Density 0.000%

    No Known Activations