© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7413
    Prev
    Next
    INDEX
    Explanations

    Python code snippets

    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_262k_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
     expliquer
    0.45
    ەک
    0.42
     diagnóstico
    0.42
     эффек
    0.42
     satiety
    0.41
    Ᏸ
    0.41
     tumeurs
    0.40
     protéines
    0.40
     массы
    0.39
     ingrédients
    0.39
    POSITIVE LOGITS
    if
    0.63
    is
    0.59
    0.59
    on
    0.57
    u
    0.55
    ol
    0.55
    ing
    0.53
    ar
    0.53
    il
    0.53
    l
    0.53
    Activations Density 0.192%

    No Known Activations