© 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. 15818
    Prev
    Next
    INDEX
    Explanations

    dealer associations, discretion, groups, innovators

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

    concept descriptions

    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
    G
    0.48
    B
    0.47
    Ｂ
    0.45
    Foster
    0.45
    க்க
    0.45
    ته
    0.44
    aboration
    0.44
    aggreg
    0.42
    J
    0.42
    ske
    0.42
    POSITIVE LOGITS
     Malang
    0.52
     Mal
    0.51
     අවශ්‍ය
    0.51
     Yeşil
    0.50
     whit
    0.50
     mlijeka
    0.49
     constitu
    0.49
     mlij
    0.48
     উপকরণ
    0.48
     perpend
    0.48
    Activations Density 0.000%

    No Known Activations