© 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. 210557
    Prev
    Next
    INDEX
    Explanations

    illustrative description of customers

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

    banking and finance

    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
    ຍ
    0.43
     đảo
    0.41
     도형
    0.40
    QFont
    0.40
    石头
    0.40
    PP
    0.40
    );//
    0.39
    KEYCODE
    0.39
    あなたは
    0.39
    贻
    0.39
    POSITIVE LOGITS
     propriet
    0.55
     lus
    0.52
     banks
    0.50
    فس
    0.50
     In
    0.48
     British
    0.47
    leges
    0.46
     CBR
    0.45
     Decline
    0.44
     lys
    0.44
    Activations Density 0.001%

    No Known Activations