© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130145
    Prev
    Next
    INDEX
    Explanations

    dates and positive affirmations

    np_acts-logits-general · gemini-2.5-flash-lite

    prediction machines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Ặ
    0.53
     vozila
    0.52
    લા
    0.51
    לק
    0.51
     Волго
    0.51
    Appellant
    0.48
    스코
    0.48
     agres
    0.48
    ந
    0.48
     agress
    0.48
    POSITIVE LOGITS
    uw
    0.46
     程
    0.46
    ter
    0.43
    ipp
    0.41
    ir
    0.40
    irin
    0.40
    ani
    0.40
    ifer
    0.40
     Chan
    0.40
    eron
    0.40
    Activations Density 0.001%

    No Known Activations