© 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. 136169
    Prev
    Next
    INDEX
    Explanations

    pets and smokers

    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
     безпе
    0.43
    Interrupt
    0.43
    Access
    0.41
    Memory
    0.41
    ேன்
    0.41
     interrupted
    0.41
     безопасность
    0.40
    欹
    0.39
    Square
    0.39
    ాత్ర
    0.39
    POSITIVE LOGITS
     Noetherian
    0.44
     acept
    0.44
     renters
    0.43
     negotiable
    0.43
     Accepted
    0.42
     vegetarians
    0.42
     convinced
    0.41
     decidido
    0.41
     किरायेदारों
    0.40
     принима
    0.40
    Activations Density 0.021%

    No Known Activations