© 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. 101808
    Prev
    Next
    INDEX
    Explanations

    reading the tag

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

    attention and inattention

    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
    อะ
    0.50
     ‘
    0.50
    ราม
    0.47
     clever
    0.47
     ава
    0.45
     settlement
    0.45
     {{
    0.43
     ಹೊಸ
    0.43
    _
    0.43
     new
    0.42
    POSITIVE LOGITS
    徫
    0.53
    ﹂
    0.52
     éviter
    0.50
    菣
    0.50
    졌
    0.50
     convexes
    0.49
     atmosfé
    0.48
     résult
    0.48
    ᕇ
    0.47
    了一眼
    0.47
    Activations Density 0.000%

    No Known Activations