© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 219895
    Prev
    Next
    INDEX
    Explanations

    timestamp without timezone or verbose

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    脓
    0.42
     delicioso
    0.39
    꿨
    0.39
     حکمت
    0.38
     \%)$,
    0.37
     Opfer
    0.37
     każdej
    0.37
     चक्रवृद्धि
    0.37
     빙
    0.37
    恽
    0.37
    POSITIVE LOGITS
     demands
    0.47
     behaviour
    0.46
    behaviour
    0.44
     header
    0.44
     '
    0.42
     capitalise
    0.41
     etc
    0.40
    header
    0.40
     resp
    0.39
    ubles
    0.39
    Activations Density 0.001%

    No Known Activations