© 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. 22789
    Prev
    Next
    INDEX
    Explanations

    concluding words

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

    you have

    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
     snorkel
    0.41
     způsob
    0.41
     조건을
    0.40
     방법에
    0.40
     зв
    0.39
     な
    0.39
    顶
    0.39
     る
    0.39
    BPACK
    0.39
    AW
    0.38
    POSITIVE LOGITS
    唵
    0.47
    Caching
    0.44
    ত্যাগ
    0.43
    hidrat
    0.43
    сила
    0.42
    示例
    0.42
     ugyan
    0.42
    ที่เป็น
    0.42
    écies
    0.41
    一组
    0.40
    Activations Density 0.000%

    No Known Activations