© 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. 41-GEMMASCOPE-2-RES-262K
    7. 56973
    Prev
    Next
    INDEX
    Explanations

    Penang Georgetown George Town

    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_all/layer_41_width_262k_l0_big
    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
    郴
    0.43
    扱う
    0.39
     Kins
    0.38
    کنش
    0.37
    扱
    0.36
     궁
    0.36
    crib
    0.35
     thing
    0.35
     kingdom
    0.35
     शाहिद
    0.35
    POSITIVE LOGITS
     Penang
    0.75
    orgetown
    0.48
     Georgetown
    0.46
    Pen
    0.45
     Andaman
    0.45
    槟
    0.45
     фено
    0.44
    檳
    0.43
    စိတ်
    0.43
    崂
    0.42
    Activations Density 0.002%

    No Known Activations