© 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. 116160
    Prev
    Next
    INDEX
    Explanations

    Copenhagen | other | second | or | their | Code

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

    cultures, meanings, and 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
    Ꭽ
    0.66
    영
    0.61
    흡
    0.59
    獸
    0.58
    안
    0.57
    Х
    0.56
    Khi
    0.55
    女
    0.55
    श
    0.54
     гимна
    0.54
    POSITIVE LOGITS
     diplomatic
    0.48
     Jura
    0.47
     metabolic
    0.45
    zler
    0.45
     display
    0.45
     pairwise
    0.44
     boli
    0.44
    agra
    0.44
    payable
    0.44
     dined
    0.44
    Activations Density 0.004%

    No Known Activations