© 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. 128993
    Prev
    Next
    INDEX
    Explanations

    construction permit

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

    progress is constant

    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
    Anne
    0.47
     Emory
    0.46
    lers
    0.44
     Endocrinology
    0.44
     rugs
    0.44
     out
    0.42
    龙
    0.41
     Civilization
    0.41
     Sneakers
    0.41
    ু
    0.41
    POSITIVE LOGITS
     desco
    0.53
    극장
    0.53
     détecter
    0.53
    सदी
    0.52
    үүл
    0.50
     datth
    0.49
    źć
    0.48
    terminus
    0.48
    цион
    0.47
    дии
    0.47
    Activations Density 0.001%

    No Known Activations