© 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. 220096
    Prev
    Next
    INDEX
    Explanations

    indie, science news, craps, dust

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

    loans and financial terms

    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
    届
    0.46
     ET
    0.44
     autori
    0.44
     aggi
    0.42
    平
    0.42
     Ac
    0.41
     三角
    0.41
     eng
    0.41
    屆
    0.41
     使
    0.40
    POSITIVE LOGITS
    Loans
    0.53
    uties
    0.51
    㧣
    0.50
    loans
    0.48
    hiva
    0.48
     loans
    0.47
     kristall
    0.44
    ImgBoard
    0.43
    ካ
    0.43
     উদ্বাস্ত
    0.43
    Activations Density 0.000%

    No Known Activations