© 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. 8500
    Prev
    Next
    INDEX
    Explanations

    Homebrew installations

    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
    ruary
    1.73
    abulary
    1.68
    erent
    1.56
     sót
    1.54
    ITING
    1.51
    编号
    1.49
    itez
    1.47
    юць
    1.44
    令
    1.42
    reda
    1.41
    POSITIVE LOGITS
    Ւ
    2.30
    ventional
    2.24
    ристо
    2.18
    vær
    2.08
    ostasis
    2.05
    break
    2.04
    culoskeletal
    2.03
     estatales
    2.00
     ketones
    1.97
     midterm
    1.93
    Activations Density 0.050%

    No Known Activations