© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 19792
    Prev
    Next
    INDEX
    Explanations

    Angular routing modules

    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
    bamos
    0.51
     orthogon
    0.50
     guérir
    0.48
    SubDirectory
    0.48
    េទ
    0.46
    ":["
    0.46
     reforzar
    0.46
     thisComponent
    0.45
    faq
    0.45
    بوط
    0.45
    POSITIVE LOGITS
    หรือ
    0.52
     किंवा
    0.44
     или
    0.42
     or
    0.42
    a
    0.41
     หรือ
    0.40
    或
    0.40
     અથવા
    0.40
    ்
    0.38
    Continued
    0.38
    Activations Density 0.000%

    No Known Activations