© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8907
    Prev
    Next
    INDEX
    Explanations

    five or numbers

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

    numbers and calculations

    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_40_width_16k_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
    十二
    0.69
     Twelve
    0.69
     XVII
    0.65
    Twelve
    0.65
    <0xB3>
    0.62
     Seventh
    0.61
     Seventeen
    0.61
    第七
    0.60
     ৬৮
    0.60
     Thirteen
    0.60
    POSITIVE LOGITS
    五
    1.27
     cinco
    1.26
     五
    1.25
     five
    1.21
     beş
    1.20
     पाँच
    1.16
     ஐந்து
    1.16
     पांच
    1.15
     fünf
    1.14
     pię
    1.14
    Activations Density 0.375%

    No Known Activations