© 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. 11794
    Prev
    Next
    INDEX
    Explanations

    monthly or yearly payments

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

    monthly or annual periods

    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
     لائ
    0.48
     մաս
    0.47
    𝕤
    0.46
     مربع
    0.46
    ൺലൈ
    0.45
     EACH
    0.45
    會在
    0.44
     مارس
    0.44
    squa
    0.44
    𝓃
    0.44
    POSITIVE LOGITS
    /
    0.55
     или
    0.55
     or
    0.54
     capabilities
    0.52
    或其他
    0.51
     किंवा
    0.50
    (
    0.48
     veya
    0.48
     ಅಥವಾ
    0.48
     showdown
    0.47
    Activations Density 0.000%

    No Known Activations