© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13012
    Prev
    Next
    INDEX
    Explanations

    address placeholder

    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
    ,{\
    1.71
     resonate
    1.66
    ractor
    1.63
     specially
    1.63
    cmds
    1.62
     researched
    1.62
     resonated
    1.61
     carefully
    1.60
    ald
    1.56
    routeProvider
    1.55
    POSITIVE LOGITS
    یوں
    2.13
    Turning
    2.03
    ی
    2.01
    u
    1.97
    c
    1.91
    uot
    1.85
    Deleting
    1.83
     controladores
    1.82
    ০
    1.81
    る
    1.79
    Activations Density 0.013%

    No Known Activations