© 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. 40-GEMMASCOPE-2-RES-65K
    4. 1028
    Prev
    Next
    INDEX
    Explanations

    spokesperson, educator, official, party

    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_40_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
     Notion
    0.40
     Eff
    0.38
     Y
    0.38
     lbs
    0.38
    wg
    0.36
    sto
    0.35
     Μ
    0.35
     vn
    0.35
     чере
    0.35
     П
    0.34
    POSITIVE LOGITS
    င့်
    0.46
     અધિકારી
    0.44
    कर्मी
    0.44
     educator
    0.43
     കേന്ദ്ര
    0.43
    伍章
    0.43
    akuza
    0.42
     spokesperson
    0.42
     कर्मी
    0.42
    Party
    0.42
    Activations Density 0.000%

    No Known Activations