© 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. 159314
    Prev
    Next
    INDEX
    Explanations

    basic opportunities in places

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

    NVIDIA, Discord, 分割, absorbed, exposed

    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
    h
    0.56
    س
    0.49
    projeto
    0.47
    ق
    0.47
    اما
    0.46
    عمل
    0.46
     Controls
    0.46
    హ
    0.44
     Actors
    0.44
    鈳
    0.44
    POSITIVE LOGITS
     industrious
    0.54
     trochę
    0.51
     тільки
    0.50
     dosy
    0.50
     już
    0.48
     bł
    0.48
     kēia
    0.48
     fervent
    0.48
     checkIf
    0.48
     inutile
    0.47
    Activations Density 0.000%

    No Known Activations