© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7025
    Prev
    Next
    INDEX
    Explanations

    Mars and Arabica beans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     middle
    1.25
     quality
    1.17
     young
    1.14
     Shak
    1.07
     Conservatory
    0.97
    佣
    0.95
     itinerant
    0.95
    middle
    0.94
     track
    0.93
    但他
    0.92
    POSITIVE LOGITS
    FONT
    2.13
     Equations
    2.11
    сли
    2.00
    钢铁
    1.99
    ließen
    1.98
     sudoku
    1.93
    ACTIONS
    1.92
    neux
    1.87
    QUESTION
    1.85
    <0xB2>
    1.84
    Activations Density 0.000%

    No Known Activations