© 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. 168935
    Prev
    Next
    INDEX
    Explanations

    loan and employment longevity

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

    understanding lists, explanations, and complex topics

    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
    GK
    0.51
    url
    0.50
    bat
    0.49
    В
    0.48
    year
    0.46
    IC
    0.46
    country
    0.46
    V
    0.45
    然后再
    0.45
    site
    0.45
    POSITIVE LOGITS
     يتعلق
    0.54
    栘
    0.50
     namelijk
    0.46
     ማለት
    0.46
     pommes
    0.45
    颓
    0.45
     faço
    0.45
    舂
    0.45
     cią
    0.44
     الصي
    0.44
    Activations Density 0.000%

    No Known Activations