© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3083
    Prev
    Next
    INDEX
    Explanations

    red paraphrase

    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
    Negative Logits
     limo
    1.86
     limousine
    1.75
     Minden
    1.44
     playGame
    1.34
     GAME
    1.34
     parib
    1.34
     giggle
    1.33
     giochi
    1.30
     instante
    1.29
    眙
    1.26
    POSITIVE LOGITS
    Fc
    1.33
    FC
    1.20
    F
    1.16
    fed
    1.15
    fs
    1.15
    fc
    1.12
    Fs
    1.06
    fts
    1.04
    Fd
    1.03
    dots
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.