© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135328
    Prev
    Next
    INDEX
    Explanations

    below, confidence, most

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

    suddenly or subtly describe feelings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tête
    0.53
     ஆரோ
    0.51
    橑
    0.48
    窍
    0.47
     Sé
    0.47
    פו
    0.47
    зло
    0.47
     Panamá
    0.47
    머
    0.46
     Commencez
    0.46
    POSITIVE LOGITS
     変
    0.54
    aku
    0.46
    website
    0.45
    ার
    0.44
    Id
    0.43
    Arrays
    0.42
    Ids
    0.42
    OrFail
    0.42
    NaN
    0.41
     Wages
    0.41
    Activations Density 0.000%

    No Known Activations