© 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. 190169
    Prev
    Next
    INDEX
    Explanations

    other news

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

    locally optimal

    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
     premat
    0.47
     സെക്രട്ട
    0.46
    썼
    0.46
    리즈
    0.45
     prematurely
    0.43
     structurally
    0.43
     boş
    0.43
     надо
    0.43
    ził
    0.43
     गर्ल्स
    0.43
    POSITIVE LOGITS
    怏
    0.47
     Aeg
    0.46
     Jeju
    0.46
     Pasteur
    0.46
    spinal
    0.45
     Zanzibar
    0.45
     Nagasaki
    0.45
     spinal
    0.45
    ชีพ
    0.44
    太陽
    0.44
    Activations Density 0.001%

    No Known Activations