© 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. 3958
    Prev
    Next
    INDEX
    Explanations

    Ctrl+C or Thursday

    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
    꿈
    1.93
    োর্ড
    1.91
    𝚊
    1.89
    𝚗
    1.87
    𝒆
    1.87
    軛
    1.86
    ᅴ
    1.80
    层的
    1.77
    𝚛
    1.77
     bắn
    1.76
    POSITIVE LOGITS
    a
    2.38
    н
    2.00
    潟
    1.91
    cito
    1.86
    aul
    1.81
    ه
    1.79
     administratif
    1.79
    jol
    1.76
    departure
    1.75
    що
    1.74
    Activations Density 0.000%

    No Known Activations