© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34966
    Prev
    Next
    INDEX
    Explanations

    rules, exceptions, objections

    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
     irregular
    0.40
     Можно
    0.40
     using
    0.39
     Skip
    0.39
     arbitrary
    0.38
     dispone
    0.38
     skip
    0.38
    ↵↵↵
    0.37
     Using
    0.37
     menyediakan
    0.37
    POSITIVE LOGITS
     作为
    0.45
    buyers
    0.45
     분위
    0.45
     최고의
    0.43
    atletas
    0.43
     diplomats
    0.41
     servicemen
    0.41
    atients
    0.41
     buyers
    0.40
    embalikan
    0.40
    Activations Density 0.000%

    No Known Activations