© 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-262K
    7. 90286
    Prev
    Next
    INDEX
    Explanations

    word endings like 'ites', 'oses', 'ts'

    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
    I
    0.59
    T
    0.54
    д
    0.49
    ِی
    0.48
    з
    0.46
    g
    0.46
    O
    0.46
    当
    0.45
    ಲ್
    0.45
    λα
    0.45
    POSITIVE LOGITS
     surfboard
    0.50
     hydrophilic
    0.49
     waterproofing
    0.48
     pria
    0.47
     oppon
    0.46
    離開
    0.45
    handed
    0.44
     ader
    0.44
     authorship
    0.43
     dikeluarkan
    0.43
    Activations Density 0.001%

    No Known Activations