© 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. 31-GEMMASCOPE-2-RES-262K
    7. 99992
    Prev
    Next
    INDEX
    Explanations

    the ordinary world

    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
     силы
    0.46
    engan
    0.45
     пред
    0.43
    eel
    0.43
     kanker
    0.43
     waktu
    0.42
    ᱭ
    0.42
     промежу
    0.41
     наиболь
    0.41
    iramente
    0.41
    POSITIVE LOGITS
    J
    0.48
     -!
    0.48
     Valuation
    0.45
     Rosen
    0.44
     WHITE
    0.44
     Snow
    0.43
     Cleveland
    0.43
     Greenhouse
    0.43
     Glas
    0.43
     Greenberg
    0.42
    Activations Density 0.000%

    No Known Activations