© 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. 3491
    Prev
    Next
    INDEX
    Explanations

    words starting with D

    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
     homologous
    1.98
    erian
    1.90
    țit
    1.84
     Defaults
    1.83
    微
    1.80
    تو
    1.75
     puțin
    1.74
    鹉
    1.70
    썩
    1.68
    TEL
    1.68
    POSITIVE LOGITS
    owntown
    1.70
    izziness
    1.59
    ział
    1.58
    ramatic
    1.58
    andelions
    1.55
    harma
    1.49
    ENSITY
    1.49
    actyl
    1.49
    eltat
    1.46
    YNAMICS
    1.45
    Activations Density 0.197%

    No Known Activations