© 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. 211126
    Prev
    Next
    INDEX
    Explanations

    glass or wooden terrace

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

    writing stories and poems

    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
     verzi
    0.57
    ટ
    0.54
     информация
    0.49
     personalizados
    0.49
     Мари
    0.49
    开始
    0.48
    थी
    0.48
     информации
    0.48
    彿
    0.48
    最初
    0.48
    POSITIVE LOGITS
     famine
    0.50
     coefficients
    0.46
     knitting
    0.46
     contribution
    0.46
     dumpling
    0.45
     starvation
    0.44
     mineral
    0.43
     baking
    0.43
     golfing
    0.43
    lair
    0.43
    Activations Density 0.000%

    No Known Activations