© 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. 3576
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    usky
    0.98
     tetrachloride
    0.89
    ともに
    0.88
     memnun
    0.84
    是中国
    0.83
    合計
    0.81
    |_{\
    0.79
    は約
    0.78
     homozygous
    0.74
    bedaan
    0.74
    POSITIVE LOGITS
    such
    4.64
     such
    4.59
     مثل
    4.56
     like
    4.53
     LIKE
    4.28
     SUCH
    4.07
    like
    4.01
     Like
    3.95
     seperti
    3.95
     เช่น
    3.81
    Activations Density 1.211%

    No Known Activations