© 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. 132705
    Prev
    Next
    INDEX
    Explanations

    financial services and benefits

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

    return amortization expense

    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
    חר
    0.50
    n
    0.49
     השני
    0.48
    t
    0.48
    PREC
    0.45
    attended
    0.45
    {
    0.44
    은
    0.44
    att
    0.44
     стри
    0.44
    POSITIVE LOGITS
    蛛
    0.55
    蚁
    0.47
     analyzers
    0.46
    ！
    0.45
    慾
    0.45
    窍
    0.44
    0.44
     Elapsed
    0.43
    喱
    0.43
    군요
    0.43
    Activations Density 0.001%

    No Known Activations