© 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. 6186
    Prev
    Next
    INDEX
    Explanations

    that promotes

    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
     Urugu
    1.07
     Jersey
    1.06
    bourg
    1.02
    かる
    1.01
    辰
    1.00
     phyll
    0.98
    少なく
    0.98
    っぱり
    0.97
     destaque
    0.97
     Phyll
    0.96
    POSITIVE LOGITS
     utveck
    1.50
     singh
    1.50
    armament
    1.49
    apeti
    1.48
    тино
    1.44
    coni
    1.44
    ckså
    1.44
    Amen
    1.42
    锄
    1.40
     altra
    1.38
    Activations Density 0.018%

    No Known Activations