© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40261
    Prev
    Next
    INDEX
    Explanations

    assumes you have

    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
     Medik
    0.45
     aprecia
    0.45
    ijk
    0.44
     intran
    0.43
    ။
    0.43
     houden
    0.42
     sende
    0.42
     lézard
    0.42
    ٓ
    0.42
     cited
    0.42
    POSITIVE LOGITS
    university
    0.44
    umsi
    0.44
     eldest
    0.43
     औपचारिक
    0.41
     fateful
    0.41
     anthropological
    0.41
    uji
    0.40
    刘
    0.40
     최종
    0.40
     골
    0.40
    Activations Density 0.001%

    No Known Activations