© 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. 133881
    Prev
    Next
    INDEX
    Explanations

    articles and common words

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

    acknowledging or supplementing

    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
    さは
    0.54
    is
    0.50
    ູບ
    0.50
     त्याच्या
    0.47
    ५
    0.47
     おり
    0.46
    embalikan
    0.46
    isah
    0.46
     व्यापक
    0.46
    ancha
    0.46
    POSITIVE LOGITS
    炲
    0.48
     অফিসের
    0.44
    的项目
    0.42
    يمة
    0.41
     List
    0.40
    ドン
    0.40
    派
    0.40
     vec
    0.39
    的其他
    0.39
     Kimura
    0.39
    Activations Density 0.001%

    No Known Activations