© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116760
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and 'with'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bulunan
    -0.06
     agribusiness
    -0.05
     সন্দে
    -0.05
     Denial
    -0.05
     those
    -0.05
    NSMutableArray
    -0.05
    那個
    -0.05
     സാധാരണ
    -0.05
    那个
    -0.05
    icuous
    -0.05
    POSITIVE LOGITS
     dengan
    0.08
     עם
    0.07
     with
    0.07
     anschließend
    0.07
     така
    0.07
    !(
    0.07
     με
    0.07
     !(
    0.07
     dando
    0.07
     با
    0.06
    Activations Density 0.001%

    No Known Activations