© 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. 5121
    Prev
    Next
    INDEX
    Explanations

    modern

    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
    ok
    0.73
    。</
    0.56
    el
    0.55
    2
    0.51
    6
    0.49
    AB
    0.49
    ak
    0.49
    ij
    0.48
    af
    0.48
    榴
    0.47
    POSITIVE LOGITS
     moderne
    1.28
     moderno
    1.16
     현대
    1.13
     modernes
    1.11
     modernos
    1.07
     modernen
    1.02
    現代
    1.01
     moderna
    0.99
     modern
    0.98
     modernas
    0.98
    Activations Density 0.035%

    No Known Activations