© 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. 186695
    Prev
    Next
    INDEX
    Explanations

    categories and headings

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

    international websites and organizational links

    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
     훨
    0.41
    ಗೂ
    0.39
    毫米
    0.38
     eighteen
    0.38
    今年は
    0.37
     Entire
    0.37
    thinmathspace
    0.37
     multiplicative
    0.36
     extensive
    0.36
     Experimental
    0.36
    POSITIVE LOGITS
     &
    0.52
     naš
    0.50
    ële
    0.50
    ²/
    0.48
    ër
    0.46
     വിശ
    0.44
     FAQs
    0.43
     faaliyet
    0.42
    çe
    0.42
     रिपोर्ट्स
    0.42
    Activations Density 0.062%

    No Known Activations