© 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. 2749
    Prev
    Next
    INDEX
    Explanations

    distinct things

    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
     vides
    2.56
    엎
    2.55
    FE
    2.24
     fe
    2.21
    ACCEPT
    2.20
     escapes
    2.20
    COMMON
    2.15
    లా
    2.14
    ﺫ
    2.14
    abcdef
    2.12
    POSITIVE LOGITS
     samym
    3.18
    ről
    3.15
    enya
    2.82
    ību
    2.76
    ruptedException
    2.72
    ン
    2.70
    arov
    2.70
    ਾ
    2.68
    िया
    2.64
    د
    2.63
    Activations Density 0.066%

    No Known Activations