© 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. 2941
    Prev
    Next
    INDEX
    Explanations

    "Attention!", "Make"

    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
     Barbosa
    1.09
    БК
    1.05
     Brito
    1.04
     ancillary
    1.03
    postgres
    1.02
     আর্কাইভ
    0.98
     interfacing
    0.97
    樍
    0.97
    },(
    0.95
     multifunctional
    0.94
    POSITIVE LOGITS
     Take
    2.89
     Somebody
    2.73
     When
    2.69
     Where
    2.68
    Take
    2.67
     Don
    2.62
     Let
    2.61
     Never
    2.61
     My
    2.61
     Into
    2.56
    Activations Density 0.187%

    No Known Activations