© 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-65K
    7. 64059
    Prev
    Next
    INDEX
    Explanations

    low cost product specifications

    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_65k_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
     .
    0.68
     and
    0.60
    is
    0.57
     World
    0.56
     was
    0.55
     Cr
    0.53
    ize
    0.52
     said
    0.52
    isa
    0.51
     ma
    0.51
    POSITIVE LOGITS
    تری
    0.51
    ovým
    0.50
    குரு
    0.50
     केंद्र
    0.49
     늘
    0.48
     കർ
    0.48
     택
    0.48
    nlü
    0.48
    fnamefont
    0.47
    INCLUDING
    0.47
    Activations Density 0.002%

    No Known Activations