© 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. 218053
    Prev
    Next
    INDEX
    Explanations

    love or associated with

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

    writing and expression across languages

    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
    mt
    0.51
    λ
    0.50
    hu
    0.46
    zeta
    0.44
    ln
    0.44
    ScreenWidth
    0.43
    vec
    0.43
    zentrum
    0.42
    ate
    0.41
    vgl
    0.41
    POSITIVE LOGITS
    سے
    0.60
     escrever
    0.59
    ی
    0.56
    س
    0.55
    ای
    0.54
     écrite
    0.52
     recommande
    0.52
    یع
    0.52
    ایج
    0.52
     volte
    0.51
    Activations Density 0.000%

    No Known Activations