© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10656
    Prev
    Next
    INDEX
    Explanations

    oligosaccharides / Robin tennis / Gretzky

    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
    Not in Any Lists

    No Comments

    Negative Logits
    る
    2.58
    ਲੇ
    2.54
    AppBar
    2.44
    نيا
    2.44
    wakilan
    2.44
    ו
    2.37
    竞争力
    2.34
    uhe
    2.31
    ווי
    2.30
    thouse
    2.24
    POSITIVE LOGITS
    olulu
    1.97
    omach
    1.93
    rr
    1.82
    exion
    1.77
     happ
    1.72
     `,
    1.70
    incidence
    1.70
     ハ
    1.65
     past
    1.61
    ാര
    1.58
    Activations Density 0.005%

    No Known Activations