© 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. 127848
    Prev
    Next
    INDEX
    Explanations

    avoid require

    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
     synchrotron
    0.49
     diffusivity
    0.47
    ៊
    0.46
    Merk
    0.45
    ｲ
    0.45
    াণিত
    0.45
     hadrons
    0.44
    aternion
    0.44
     vortices
    0.43
     tokamaks
    0.43
    POSITIVE LOGITS
     दोन्ही
    0.54
     कोणत्याही
    0.48
    é
    0.48
     Paw
    0.47
    饮食
    0.47
     começar
    0.46
     nėra
    0.46
     начинают
    0.45
     feme
    0.45
     başına
    0.44
    Activations Density 0.009%

    No Known Activations