© 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. 6347
    Prev
    Next
    INDEX
    Explanations

    recommended ways

    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
    PRESENT
    1.54
    Brazil
    1.53
    或者
    1.53
    娅
    1.52
    EXIST
    1.52
    或者是
    1.51
    swith
    1.50
     précisément
    1.50
     '</
    1.50
    ּ
    1.49
    POSITIVE LOGITS
    yata
    1.05
    faktor
    1.05
    ülü
    1.03
     eased
    1.02
     terrier
    1.01
    늠
    0.99
     endonuclease
    0.99
    数は
    0.99
    eniz
    0.97
     Pledge
    0.94
    Activations Density 0.011%

    No Known Activations