© 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. 19652
    Prev
    Next
    INDEX
    Explanations

    field definition or attribute

    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
    सायिक
    0.50
    Cemento
    0.49
    〝
    0.49
    remeno
    0.47
    िद
    0.47
    itudinal
    0.46
    ﻛ
    0.46
     कराते
    0.45
    Arithmetic
    0.45
    <0xEC>
    0.44
    POSITIVE LOGITS
     exclusivity
    0.48
     any
    0.48
     bunting
    0.41
     любой
    0.41
     `<=
    0.41
    ب
    0.41
    م
    0.40
     Ваши
    0.39
    د
    0.39
     (
    0.39
    Activations Density 0.003%

    No Known Activations