© 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. 5603
    Prev
    Next
    INDEX
    Explanations

    resolutions and storage sizes

    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
     връ
    1.55
    ̦
    1.48
    üse
    1.48
     przech
    1.48
     sét
    1.47
     leçon
    1.46
    훈련
    1.46
     ամ
    1.45
    춰
    1.45
     vorbere
    1.45
    POSITIVE LOGITS
    suits
    1.20
     TOTAL
    1.15
    TOTAL
    1.14
     solvency
    1.13
    ｘ
    1.11
    fatt
    1.10
    Total
    1.08
    зме
    1.07
    binder
    1.07
     money
    1.04
    Activations Density 0.058%

    No Known Activations