© 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. 222820
    Prev
    Next
    INDEX
    Explanations

    finance loans and payments

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

    even if

    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
    diği
    0.49
    elajaran
    0.48
     ještě
    0.47
    Î
    0.47
     tâ
    0.46
     beschäft
    0.46
     važ
    0.45
     vhodné
    0.45
    olive
    0.44
    বিট
    0.44
    POSITIVE LOGITS
     CRT
    0.51
    s
    0.47
     (,
    0.45
     م
    0.44
    िज
    0.43
    да
    0.42
     لن
    0.42
     total
    0.42
     स्वर
    0.41
     продолжает
    0.41
    Activations Density 0.000%

    No Known Activations