© 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. 73571
    Prev
    Next
    INDEX
    Explanations

    words ending with "ing" or "r"

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

    end of sentence punctuation

    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
    าว
    0.62
     spéciale
    0.54
    纮
    0.50
    дные
    0.49
     ingrédients
    0.49
    禪
    0.49
    νας
    0.49
     mensagens
    0.49
    шке
    0.48
    ധിപ
    0.48
    POSITIVE LOGITS
    ute
    0.55
    op
    0.50
    ing
    0.48
    r
    0.48
    ermek
    0.47
    anchi
    0.47
    ovan
    0.46
    utus
    0.46
    rime
    0.46
    oin
    0.45
    Activations Density 0.001%

    No Known Activations