© 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. 89016
    Prev
    Next
    INDEX
    Explanations

    financial explanations business banking

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

    qualified descriptions

    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
    /),
    0.43
     characterized
    0.41
     কার্যকলাপ
    0.40
     తేదీ
    0.40
     imperialism
    0.39
    yuan
    0.39
     kür
    0.39
    auch
    0.38
     about
    0.38
     acquis
    0.38
    POSITIVE LOGITS
    젹
    0.54
     consiglio
    0.53
    ПО
    0.52
    헹
    0.49
    Якщо
    0.49
    до
    0.47
    Пі
    0.47
    সেল
    0.47
     Після
    0.46
    뽁
    0.46
    Activations Density 0.000%

    No Known Activations