© 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. 43913
    Prev
    Next
    INDEX
    Explanations

    money and financial terms

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

    dice translation

    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
    問題を
    0.52
    ್ಯೂ
    0.48
    LER
    0.48
     madde
    0.46
    кус
    0.46
     பங்கே
    0.46
    捷
    0.45
    ニュ
    0.44
    RESOL
    0.44
     समक्ष
    0.44
    POSITIVE LOGITS
     shillings
    0.42
     rupees
    0.42
     samot
    0.41
     لیتے
    0.40
    loans
    0.40
     plums
    0.40
     browns
    0.40
    ppo
    0.39
     sharpness
    0.38
     ሽፋ
    0.38
    Activations Density 0.000%

    No Known Activations