© 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. 3616
    Prev
    Next
    INDEX
    Explanations

    Lily and female names

    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
     COLLATE
    2.10
    FTWARE
    2.06
     $('
    2.05
     }}(\
    2.02
    OURCES
    1.94
     unsurpassed
    1.92
    ractors
    1.91
    icoter
    1.91
    ascin
    1.90
     $('<
    1.90
    POSITIVE LOGITS
     reunion
    2.24
     bébé
    2.20
     everyone
    2.17
     kids
    2.09
     dinner
    2.07
     girls
    2.03
     Aunt
    2.02
     everybody
    2.00
     evacuation
    1.98
     breakfast
    1.96
    Activations Density 0.181%

    No Known Activations