© 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. 10253
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a colon

    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
    நர்
    1.72
    녁
    1.66
    투자
    1.66
    akkhati
    1.65
    ㄵ
    1.64
    댜
    1.62
    evším
    1.60
    燵
    1.58
    覦
    1.56
    netHex
    1.55
    POSITIVE LOGITS
    s
    1.94
    ات
    1.93
    та
    1.62
    ي
    1.60
    т
    1.57
    м
    1.57
    os
    1.53
    ్
    1.52
    на
    1.51
    в
    1.50
    Activations Density 0.071%

    No Known Activations