© 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. 13350
    Prev
    Next
    INDEX
    Explanations

    "What", "which" questions

    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
    我又
    0.50
    並
    0.50
    我自己
    0.46
    又
    0.44
     мои
    0.41
     خودم
    0.40
    レ
    0.40
    并
    0.39
    我們
    0.39
    clide
    0.39
    POSITIVE LOGITS
     artyku
    0.50
    文中
    0.46
     presumably
    0.44
     chyba
    0.44
     implied
    0.43
    presumably
    0.43
     perjud
    0.43
     periodistas
    0.42
     mencion
    0.41
     telephones
    0.40
    Activations Density 0.003%

    No Known Activations