© 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. 6424
    Prev
    Next
    INDEX
    Explanations

    t-shirt combinations

    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
    択
    1.28
    erview
    1.26
    leting
    1.26
    ungkinan
    1.20
    doors
    1.18
     urme
    1.18
     تضيفلها
    1.18
     WARRANTIES
    1.17
     シル
    1.14
    다음
    1.14
    POSITIVE LOGITS
     snacks
    1.58
    跑
    1.58
     жид
    1.57
     Rugby
    1.55
     '|
    1.49
    diver
    1.49
     americana
    1.47
     skateboard
    1.46
     военной
    1.46
    civil
    1.44
    Activations Density 0.027%

    No Known Activations