© 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. 241486
    Prev
    Next
    INDEX
    Explanations

    building technical concepts

    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
    _{
    0.47
    ール
    0.46
     нередко
    0.46
    ddots
    0.44
    mon
    0.42
     '?
    0.41
    sear
    0.41
    _{,
    0.41
    (\
    0.41
     poissons
    0.41
    POSITIVE LOGITS
     zawiera
    0.52
    的技术
    0.52
    全新的
    0.52
    并且
    0.51
    构建
    0.51
     Technologie
    0.50
    Technische
    0.49
     Teknik
    0.47
     rebuild
    0.47
     wraz
    0.47
    Activations Density 0.001%

    No Known Activations