© 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. 5446
    Prev
    Next
    INDEX
    Explanations

    your information improves the outcome

    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
     ✨
    1.72
    🌟
    1.70
     Fuck
    1.68
     Princess
    1.60
     Spotify
    1.59
     Pop
    1.59
     Mard
    1.59
    🥁
    1.57
    🔟
    1.57
     Prince
    1.57
    POSITIVE LOGITS
     oftentimes
    2.11
    >/</
    2.08
    尤其是
    2.05
     generalmente
    2.05
    特别是
    2.01
     علاقوں
    2.00
     geralmente
    2.00
     kadang
    1.95
    generally
    1.94
     biasanya
    1.94
    Activations Density 0.165%

    No Known Activations