© 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. 81803
    Prev
    Next
    INDEX
    Explanations

    games, men, and grind

    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
     सरस्वती
    0.52
     McKenna
    0.48
     mostrado
    0.44
    Emmanuel
    0.44
     нев
    0.43
    superblock
    0.42
    观念
    0.42
    <unused693>
    0.42
    स्तिक
    0.41
    课堂
    0.41
    POSITIVE LOGITS
    ،
    0.48
    س
    0.47
     to
    0.46
    :
    0.42
    ای
    0.41
     λοι
    0.41
     و
    0.41
     pulleys
    0.41
     components
    0.39
     одного
    0.39
    Activations Density 0.013%

    No Known Activations