© 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. 233668
    Prev
    Next
    INDEX
    Explanations

    business potential, owners, models, cases

    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
    ش
    0.54
    anı
    0.53
    ől
    0.51
    Workers
    0.50
    ş
    0.50
    industrial
    0.49
    İ
    0.49
    ten
    0.48
    Commercial
    0.47
    ime
    0.46
    POSITIVE LOGITS
     Business
    0.60
     Transactions
    0.57
     説明
    0.56
     Биз
    0.55
     丿
    0.52
     negócio
    0.50
     business
    0.50
     Rules
    0.50
     \{
    0.49
     หนึ่ง
    0.48
    Activations Density 0.081%

    No Known Activations