© 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. 15583
    Prev
    Next
    INDEX
    Explanations

    stages or sections A through E

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

    indexing sequential items or options

    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
    杽
    0.41
    䓶
    0.35
     ફિલ્મ
    0.35
    怸
    0.35
    mainwindow
    0.34
    میل
    0.34
    นัก
    0.34
     त्यानंतर
    0.34
     पिक्चर
    0.33
    竻
    0.33
    POSITIVE LOGITS
     II
    0.48
    0.48
     X
    0.48
     A
    0.46
     B
    0.45
     C
    0.44
     D
    0.44
     III
    0.44
     I
    0.43
     J
    0.43
    Activations Density 0.159%

    No Known Activations