© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12554
    Prev
    Next
    INDEX
    Explanations

    complex numbers and data tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ꮲ
    0.42
    ((*
    0.41
    Salv
    0.41
     novels
    0.41
    Leaks
    0.41
    Շ
    0.40
     faculties
    0.40
     Engels
    0.39
    oplanes
    0.39
     leakage
    0.39
    POSITIVE LOGITS
    kar
    0.44
    相談
    0.41
    gek
    0.40
    mtr
    0.40
    讓他
    0.40
     perkara
    0.39
     словарь
    0.39
    ore
    0.39
    \},
    0.39
    istiwa
    0.39
    Activations Density 0.020%

    No Known Activations