© 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. 222521
    Prev
    Next
    INDEX
    Explanations

    follow us on tweets, instagram, google plus

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

    numbers, titles, or specific terms

    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
    eren
    0.49
     важней
    0.45
     superficies
    0.43
    a
    0.43
    :
    0.41
     redesigned
    0.41
     chairs
    0.41
    onents
    0.41
    ຈ
    0.41
    curvature
    0.40
    POSITIVE LOGITS
     робити
    0.45
    学习
    0.43
     Weddings
    0.43
    🔄
    0.42
     Bachchan
    0.42
     kali
    0.40
    就会
    0.40
     kuch
    0.40
    🌯
    0.40
     Архі
    0.39
    Activations Density 0.001%

    No Known Activations