© 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. 209238
    Prev
    Next
    INDEX
    Explanations

    remarkable day, class racing, devilishly

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

    specific words or phrases in context

    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
    䂧
    0.52
     ಆಹಾರ
    0.50
     możemy
    0.48
    ₴
    0.48
     アクセサリー
    0.47
     yanı
    0.47
     আগমন
    0.47
    🕺
    0.46
    👠
    0.46
     believing
    0.46
    POSITIVE LOGITS
    -
    0.52
    ailleurs
    0.52
     Nakh
    0.48
    aruh
    0.47
    zenesulf
    0.46
    os
    0.45
    anes
    0.45
    0.45
    angkutan
    0.43
    ének
    0.42
    Activations Density 0.001%

    No Known Activations