© 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. 219093
    Prev
    Next
    INDEX
    Explanations

    foreign languages and places

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

    less catastrophic than

    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
     مای
    0.48
     اق
    0.44
     الگ
    0.44
    Inserting
    0.44
    ವರೆ
    0.44
    sped
    0.43
    Referee
    0.43
    ਫ
    0.43
     జీ
    0.42
    Eigen
    0.42
    POSITIVE LOGITS
     Comunic
    0.56
     şark
    0.51
     volontà
    0.51
     Unisex
    0.51
     Orient
    0.50
     Dominican
    0.50
     renk
    0.50
     Mozambique
    0.49
     musica
    0.48
     Emirati
    0.47
    Activations Density 0.000%

    No Known Activations