© 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. 145805
    Prev
    Next
    INDEX
    Explanations

    before, after, readable, favor

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

    placement before

    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
    多少
    0.49
    其他
    0.41
    的功能
    0.41
    ವುದ
    0.39
    EXAMPLE
    0.39
    ‌شده
    0.38
    以
    0.38
    佈
    0.38
               
    0.38
    一切
    0.38
    POSITIVE LOGITS
    تیب
    0.43
     reopened
    0.43
     सरफेस
    0.43
     veröffent
    0.42
     Vanden
    0.42
     responden
    0.41
     exclaimed
    0.41
     poursuit
    0.41
     ferrovi
    0.41
     uczni
    0.40
    Activations Density 0.002%

    No Known Activations