© 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. 4034
    Prev
    Next
    INDEX
    Explanations

    SVG path attribute `d`

    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
    ścić
    2.51
    erden
    2.49
     conferma
    2.46
    ולנד
    2.42
     portare
    2.41
     pokrač
    2.41
    ে
    2.35
    vgili
    2.32
    kében
    2.32
    る
    2.30
    POSITIVE LOGITS
    𝗲
    2.20
    𝗶
    2.02
    imeter
    1.87
    𝗮
    1.86
    ibility
    1.81
    𝗻
    1.79
    izable
    1.78
    ifies
    1.77
     cohes
    1.77
     across
    1.77
    Activations Density 0.049%

    No Known Activations