© 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. 106560
    Prev
    Next
    INDEX
    Explanations

    specific word pairs

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

    address this / columns

    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
    ly
    0.50
     sheer
    0.49
     exercising
    0.46
     ¥
    0.44
     hand
    0.43
     fundamental
    0.43
     auto
    0.43
     virtue
    0.43
     training
    0.42
     Pro
    0.41
    POSITIVE LOGITS
    ırmızı
    0.63
    🧿
    0.61
    🍮
    0.60
     Алексей
    0.59
    🚍
    0.59
    ⏹
    0.57
     Дмитрий
    0.57
    quando
    0.57
    Selecion
    0.55
     davranış
    0.55
    Activations Density 0.000%

    No Known Activations