© 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. 2963
    Prev
    Next
    INDEX
    Explanations

    in terms of

    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
    de
    2.85
    ك
    2.72
    在
    2.58
    ৮
    2.39
    g
    2.39
    te
    2.26
    ದ
    2.20
    에
    2.19
    tt
    2.19
    क
    2.17
    POSITIVE LOGITS
     accordance
    3.00
     conjunction
    2.91
     vitro
    2.83
     lieu
    2.78
     vivo
    2.76
    middels
    2.65
    cursion
    2.59
     rámci
    2.54
     terms
    2.50
    ositol
    2.42
    Activations Density 0.184%

    No Known Activations