© 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. 22341
    Prev
    Next
    INDEX
    Explanations

    market decisions and evaluations

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

    qualified positive or negative sentiment

    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
    只是
    0.44
    verbal
    0.44
    start
    0.43
    rooted
    0.42
    dependency
    0.42
    唯一
    0.42
     ذاتی
    0.41
    把它
    0.40
    ++
    0.40
    roots
    0.40
    POSITIVE LOGITS
     unfavourable
    0.64
     oldukça
    0.62
     весьма
    0.59
     bulunmaktadır
    0.57
     상당히
    0.54
    良好的
    0.54
     illetve
    0.53
     favourably
    0.52
     unfavorable
    0.51
     काफी
    0.51
    Activations Density 0.013%

    No Known Activations