© 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-65K
    7. 30796
    Prev
    Next
    INDEX
    Explanations

    games and simulations

    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_65k_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
    妍
    0.44
    湿
    0.41
     ağırl
    0.41
     infantry
    0.39
    Rotatef
    0.39
     trội
    0.39
     Mér
    0.39
     cull
    0.39
    兹
    0.38
    நட
    0.38
    POSITIVE LOGITS
     hotels
    0.42
     Pong
    0.42
     ball
    0.41
     Boat
    0.41
    pong
    0.41
     goalie
    0.41
    itoa
    0.41
    epend
    0.40
     pong
    0.40
    ola
    0.39
    Activations Density 0.069%

    No Known Activations