© 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. 108717
    Prev
    Next
    INDEX
    Explanations

    long words ending in ification and specific terms

    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
    =
    0.54
     =-
    0.50
     z
    0.50
    <0x0D>
    0.48
    +
    0.48
    )=
    0.48
    ↵
    0.47
    =-
    0.47
    =>
    0.47
     topic
    0.46
    POSITIVE LOGITS
    alade
    0.54
    urusan
    0.54
    катери
    0.52
     chamado
    0.50
     milhões
    0.50
     desenvolvido
    0.49
    🧖
    0.48
    γκεκρι
    0.48
    ಬ್ಬಳ್ಳಿ
    0.48
     partai
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.