© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10311
    Prev
    Next
    INDEX
    Explanations

    simple, inexpensive, cheap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     touching
    0.52
    a
    0.51
    น
    0.50
     unw
    0.49
     sufficiently
    0.47
     shaking
    0.47
    न
    0.47
     frivolous
    0.47
     dusty
    0.46
     reliable
    0.46
    POSITIVE LOGITS
    tsó
    0.97
     mengalami
    0.85
     브랜드
    0.83
     ezingu
    0.82
    쾺
    0.82
     berasal
    0.82
    swadian
    0.82
    들은
    0.81
    ']]
    0.81
     rappresenta
    0.81
    Activations Density 0.081%

    No Known Activations