© 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. 8918
    Prev
    Next
    INDEX
    Explanations

    Subaru, Outback, Forester

    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
    尴
    0.41
    槽
    0.41
    𝑧
    0.39
     लकार
    0.39
    痠
    0.39
    issus
    0.38
    ATOM
    0.38
    ួរ
    0.38
     germinate
    0.37
     spanish
    0.37
    POSITIVE LOGITS
     Subaru
    1.30
     Outback
    0.68
     Forester
    0.66
     Sub
    0.59
     Boxer
    0.58
    Fuj
    0.57
     Fuji
    0.56
    昴
    0.55
     WR
    0.55
     SUB
    0.54
    Activations Density 0.003%

    No Known Activations