© 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. 17452
    Prev
    Next
    INDEX
    Explanations

    March 31

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

    value and existence

    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
     hỏi
    0.51
     মাধ
    0.47
     रिव
    0.47
     borrowings
    0.47
    പറ
    0.47
     গ্রস্থ
    0.46
     پیشن
    0.46
    햐
    0.46
    PointCloud
    0.45
     tampak
    0.45
    POSITIVE LOGITS
    省级
    0.51
     chem
    0.45
     fulfills
    0.43
    逻
    0.43
     cambio
    0.43
     physico
    0.41
     placer
    0.41
    废物
    0.41
    čí
    0.41
     stabile
    0.41
    Activations Density 0.000%

    No Known Activations