© 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. 10386
    Prev
    Next
    INDEX
    Explanations

    investigation into

    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
    thood
    2.71
    bolic
    2.70
    ული
    2.70
    殑
    2.65
    лил
    2.49
     Éireann
    2.48
    ϊ
    2.47
    সেই
    2.46
    regelen
    2.45
    ヤー
    2.45
    POSITIVE LOGITS
    e
    3.07
    a
    2.82
    im
    2.65
    ܛ
    2.63
    et
    2.54
    ा
    2.51
    ோ
    2.47
    emar
    2.44
     abrigo
    2.40
    ו
    2.39
    Activations Density 0.023%

    No Known Activations