© 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. 32885
    Prev
    Next
    INDEX
    Explanations

    experimental outcomes and biological phenotypes

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

    Default Port

    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
     construc
    0.84
     acknow
    0.76
    4
    0.75
     representa
    0.73
     transforma
    0.71
     accom
    0.70
     administra
    0.68
    3
    0.66
    6
    0.65
    5
    0.64
    POSITIVE LOGITS
     mempert
    0.48
    வாழ்
    0.46
    牺
    0.45
     、,
    0.44
    நிதி
    0.44
     gacche
    0.44
     بیاکتنې
    0.44
     ऑफिसियल
    0.43
     ماشینونه
    0.43
     言っ
    0.43
    Activations Density 0.003%

    No Known Activations