© 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. 223846
    Prev
    Next
    INDEX
    Explanations

    business and finance

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

    debt incurred

    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
    ools
    0.47
    fuzzy
    0.47
    mdp
    0.46
    cknow
    0.46
    FLOW
    0.46
    cknowled
    0.45
    ggi
    0.44
    t
    0.44
    MODE
    0.44
    FISH
    0.44
    POSITIVE LOGITS
     በ
    0.47
    我们也
    0.46
     asuntos
    0.45
    कृष्ण
    0.45
     چنان
    0.44
     ۸
    0.44
     polymorphic
    0.43
     شكله
    0.43
     autores
    0.43
     Violet
    0.43
    Activations Density 0.001%

    No Known Activations