© 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. 4623
    Prev
    Next
    INDEX
    Explanations

    cases where

    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
     grandson
    0.86
     Plut
    0.84
     ........
    0.83
     stoff
    0.83
     Statue
    0.81
    UU
    0.80
     Estat
    0.80
    ("["
    0.79
     ?"
    0.78
     Catalogue
    0.78
    POSITIVE LOGITS
    ricas
    1.64
    UTRAL
    1.62
    克斯
    1.59
    ksam
    1.54
    avorable
    1.53
    ksa
    1.53
     hilfreich
    1.52
    ผ่านมา
    1.51
     validating
    1.51
     maximized
    1.51
    Activations Density 0.126%

    No Known Activations