© 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. 131122
    Prev
    Next
    INDEX
    Explanations

    water, second, largest, again

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

    listing options or classifications

    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
    ial
    0.49
    os
    0.45
    2
    0.45
    ate
    0.44
    (
    0.44
    、
    0.44
    ient
    0.42
    ات
    0.42
    今まで
    0.42
    总
    0.41
    POSITIVE LOGITS
     peony
    0.59
     francesa
    0.55
    centes
    0.55
     penguins
    0.54
     peonies
    0.54
     ಕುಟುಂಬ
    0.54
     amigas
    0.53
     alemán
    0.53
     มั้ย
    0.51
    cón
    0.50
    Activations Density 0.001%

    No Known Activations