© 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. 14453
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT

    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
    fd
    1.17
    ella
    1.06
    (|
    1.06
     बजा
    1.05
    ixen
    1.04
    =>{
    1.04
    е
    1.03
    あります
    1.01
    (<
    1.01
    <a>
    1.01
    POSITIVE LOGITS
    raient
    1.49
    𝖘
    1.47
    ا
    1.45
    sız
    1.38
    ړو
    1.35
     envelopp
    1.34
    цо
    1.34
    𝐚
    1.33
     avanzar
    1.31
    eraient
    1.30
    Activations Density 0.032%

    No Known Activations