© 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. 42920
    Prev
    Next
    INDEX
    Explanations

    complexity, class, light, photon, audio

    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
    ऱ्या
    0.43
    {#
    0.40
     gallium
    0.40
     querem
    0.40
    ’
    0.40
     figurine
    0.39
     تريد
    0.39
    igan
    0.39
     housewife
    0.39
    tenberg
    0.39
    POSITIVE LOGITS
     ומ
    0.48
    ม
    0.47
    缫
    0.47
    З
    0.47
    мо
    0.45
    សិក
    0.43
     IT
    0.43
    文学
    0.42
     ov
    0.42
    Во
    0.42
    Activations Density 0.006%

    No Known Activations