© 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. 24589
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    section headings and subsequent formatting

    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
    én
    0.43
    岃
    0.43
    ुलेंस
    0.41
    auern
    0.40
    izado
    0.40
    य़
    0.39
    ước
    0.38
    ulaire
    0.38
    öd
    0.38
    øy
    0.38
    POSITIVE LOGITS
    ↵
    0.36
    分别是
    0.35
    に対する
    0.35
     wellknown
    0.34
     ഏ
    0.34
    subequations
    0.33
          
    0.33
    ）：
    0.32
    ↵↵↵↵↵
    0.32
     r
    0.32
    Activations Density 0.014%

    No Known Activations