© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 170
    Prev
    Next
    INDEX
    Explanations

    organizations, observations, Russian, Pig Latin

    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_all/layer_41_width_262k_l0_big
    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
     optimizes
    0.40
     composite
    0.38
     adjustable
    0.37
     thresholds
    0.37
     glycemic
    0.36
     intervals
    0.36
    proficiency
    0.35
     ø
    0.35
     permeability
    0.35
     xy
    0.35
    POSITIVE LOGITS
    די
    0.45
    ט
    0.41
    לה
    0.40
    ilah
    0.40
    Storia
    0.39
     Groupon
    0.39
     Biblioteca
    0.38
     Museo
    0.38
     Estudios
    0.38
    罍
    0.38
    Activations Density 0.032%

    No Known Activations