© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 165745
    Prev
    Next
    INDEX
    Explanations

    clear zero tolerance

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

    strong economic indicators

    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
     I
    0.55
     Y
    0.53
     A
    0.49
    J
    0.48
     Background
    0.47
    ↵↵
    0.46
    本人
    0.46
    G
    0.46
    IOException
    0.46
    Background
    0.46
    POSITIVE LOGITS
     смартфо
    0.58
     школи
    0.56
    वाड़ा
    0.55
     слабы
    0.55
     condemning
    0.54
     школ
    0.54
     lettere
    0.53
     школы
    0.52
     nghiêm
    0.52
     phận
    0.52
    Activations Density 0.000%

    No Known Activations