© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8089
    Prev
    Next
    INDEX
    Explanations

    paint or coatings use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     посо
    0.52
     sampah
    0.50
    ⸩
    0.46
     приве
    0.46
     साहस
    0.45
     reassured
    0.44
    ભાઈ
    0.44
     бир
    0.43
     стратегиясе
    0.43
     социа
    0.43
    POSITIVE LOGITS
     coating
    1.16
     coatings
    1.07
     Coating
    1.06
    coating
    1.03
    涂
    0.95
     Coatings
    0.88
    塗
    0.82
     varnish
    0.80
     paint
    0.77
    Paint
    0.73
    Activations Density 0.298%

    No Known Activations