© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7120
    Prev
    Next
    INDEX
    Explanations

    with certainty

    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
    Negative Logits
    kolah
    1.62
    uper
    1.60
    teen
    1.43
    rocess
    1.32
    atih
    1.30
     parent
    1.29
    kid
    1.28
    wner
    1.27
     mario
    1.26
    딸
    1.25
    POSITIVE LOGITS
    iment
    1.22
     pubblico
    1.10
    つもり
    1.09
     estómago
    1.08
    桁
    1.06
    pieces
    1.04
     Bots
    1.03
    次第
    1.02
     nombre
    1.02
    iments
    1.02
    Activations Density 0.035%

    No Known Activations