© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5049
    Prev
    Next
    INDEX
    Explanations

    exception as e

    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
     Jorn
    1.54
     moitié
    1.53
     dermatitis
    1.46
     gând
    1.43
     Ferté
    1.43
    ofi
    1.42
    anjan
    1.41
    諷
    1.40
     mitad
    1.40
     mockup
    1.37
    POSITIVE LOGITS
    agod
    0.93
    ertal
    0.92
    icea
    0.88
     Kig
    0.84
    ɫ
    0.83
    jelder
    0.81
    ADS
    0.80
    inguistic
    0.79
    ǝ
    0.78
    kis
    0.76
    Activations Density 0.002%

    No Known Activations