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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 522
    Prev
    Next
    INDEX
    Explanations

    programming terms and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     countless
    1.07
    ЛИ
    1.06
     egregious
    1.05
     florals
    1.03
    ظ
    1.02
    РА
    1.00
     restless
    0.99
    umbuhan
    0.97
     apocalyptic
    0.96
     fantastical
    0.96
    POSITIVE LOGITS
    _
    1.26
     spp
    0.99
    \_
    0.94
     docket
    0.92
    த்
    0.92
    info
    0.91
    Info
    0.90
     presso
    0.87
    本体
    0.86
     tycker
    0.85
    Activations Density 3.393%

    No Known Activations