© 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. 31-GEMMASCOPE-2-RES-262K
    7. 90460
    Prev
    Next
    INDEX
    Explanations

    failing/declined transactions

    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_31_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
     Announces
    0.46
    لية
    0.46
    agogue
    0.44
    潋
    0.43
    依旧
    0.43
    މ
    0.43
    образной
    0.43
    ostatistics
    0.43
     kosten
    0.42
    ließt
    0.42
    POSITIVE LOGITS
     aigu
    0.47
     bên
    0.47
     payments
    0.46
     dễ
    0.45
     đích
    0.44
    天
    0.44
     dependents
    0.44
    aigu
    0.44
    iop
    0.43
     chỉ
    0.43
    Activations Density 0.001%

    No Known Activations