© 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. 228537
    Prev
    Next
    INDEX
    Explanations

    by the quantity or container

    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
    萩
    0.45
     partially
    0.43
     exot
    0.43
    大
    0.43
    本体
    0.43
    日常
    0.42
     asterisk
    0.41
     pathogenic
    0.41
    天
    0.40
    0.39
    POSITIVE LOGITS
     ወይም
    0.62
     或者
    0.54
     précédente
    0.52
     başka
    0.51
    ᆹ
    0.51
     ಅಥವಾ
    0.50
     때
    0.50
     לפי
    0.49
    齙
    0.49
     లేదా
    0.49
    Activations Density 0.006%

    No Known Activations