© 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. 182260
    Prev
    Next
    INDEX
    Explanations

    Spinach leaves, coconut milk

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

    reports and people's experiences

    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
    ס
    0.49
    ంది
    0.48
    сіі
    0.47
    ड़ा
    0.47
    нды
    0.47
    ስ
    0.47
    蚪
    0.46
    änder
    0.46
    స్
    0.45
    ಗೆ
    0.45
    POSITIVE LOGITS
     gravitate
    0.52
     giảng
    0.48
     آسم
    0.48
    ARB
    0.47
     Mao
    0.46
     &
    0.46
    ช่วยเหลือ
    0.44
     特に
    0.44
     এমনকি
    0.43
     paš
    0.43
    Activations Density 0.000%

    No Known Activations