© 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. 116645
    Prev
    Next
    INDEX
    Explanations

    negation, absence, exclusivity, or concession

    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
     those
    -0.07
     sicuro
    -0.06
     З
    -0.06
     թ
    -0.06
     thofe
    -0.05
     celui
    -0.05
    cro
    -0.05
     graciously
    -0.05
     ث
    -0.05
     ইতিহাস
    -0.05
    POSITIVE LOGITS
     tento
    0.07
     hiçbir
    0.07
     oraz
    0.07
    tono
    0.07
    没有任何
    0.07
     بدون
    0.07
     ine
    0.07
    ുവരി
    0.06
    KOM
    0.06
     මෙම
    0.06
    Activations Density 0.025%

    No Known Activations