© 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. 53508
    Prev
    Next
    INDEX
    Explanations

    once upon a time

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

    Once upon a time

    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
    톈
    0.49
    ጣጠ
    0.43
    heits
    0.42
    CAM
    0.42
     വ്യ
    0.42
     緊急
    0.42
    FDMA
    0.41
    Ϊ
    0.41
    िश्चित
    0.41
    ächs
    0.40
    POSITIVE LOGITS
     ChatGPT
    0.46
     Spotify
    0.46
     Peck
    0.42
     নিয়মিত
    0.42
     Salt
    0.41
     Sampson
    0.41
     каждую
    0.40
    </code>
    0.39
     Pe
    0.38
    腼
    0.38
    Activations Density 0.000%

    No Known Activations