© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6536
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by bold marker

    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_15_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
     youngsters
    1.82
     youths
    1.80
     kinderg
    1.72
     videogame
    1.71
    innie
    1.70
    <0x0D>
    1.70
     childhood
    1.67
    シャフト
    1.63
     habitants
    1.63
     ";
    1.62
    POSITIVE LOGITS
     pār
    0.96
     dupatta
    0.91
     băng
    0.85
     saam
    0.81
     거짓
    0.81
     falsa
    0.80
     kontra
    0.80
     verme
    0.79
     slutt
    0.79
     verre
    0.79
    Activations Density 0.047%

    No Known Activations