© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3694
    Prev
    Next
    INDEX
    Explanations

    day 2 itinerary

    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_12_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
     Katy
    1.67
     millet
    1.64
     Suppose
    1.63
     Hartree
    1.62
     Darling
    1.61
    呤
    1.56
     Gandhiji
    1.56
    Nonnull
    1.55
     Jeter
    1.54
     Specify
    1.53
    POSITIVE LOGITS
    样
    1.41
    conditioning
    1.26
    樣
    1.24
     laun
    1.24
    rouw
    1.22
    uite
    1.19
    hood
    1.18
    evo
    1.17
    alous
    1.16
     vess
    1.16
    Activations Density 0.000%

    No Known Activations