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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106887
    Prev
    Next
    INDEX
    Explanations

    agreement and consent

    np_acts-logits-general · gemini-2.5-flash-lite

    Marxist concepts and Norway Bans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Collin
    0.49
     كوساين
    0.47
    Fuse
    0.46
    ্বরের
    0.45
    拉斯
    0.44
    fuse
    0.44
    Cosine
    0.44
    粗
    0.43
    秵
    0.43
    身份证
    0.43
    POSITIVE LOGITS
     £
    0.57
     गाड़ी
    0.49
     frosting
    0.45
     refrigerant
    0.44
     acid
    0.43
     camion
    0.43
     गाड़ी
    0.43
     Bradford
    0.43
     organise
    0.43
     spurt
    0.43
    Activations Density 0.000%

    No Known Activations