© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4307
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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_17_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
     legitim
    0.91
     enjeux
    0.89
     креди
    0.89
     podat
    0.88
     mondiale
    0.88
    Eksterne
    0.86
     vetting
    0.85
    ⼯
    0.85
     esigen
    0.85
    ISION
    0.85
    POSITIVE LOGITS
     thậm
    1.19
     sometimes
    1.08
     occasionally
    1.08
     possible
    1.06
     amusing
    1.04
     diameters
    1.03
     variations
    1.03
     variation
    1.00
     even
    1.00
     occasional
    0.99
    Activations Density 0.736%

    No Known Activations