© 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. 120187
    Prev
    Next
    INDEX
    Explanations

    titles and subtitles

    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
    .
    -0.06
     circumstances
    -0.06
     those
    -0.06
     circumstance
    -0.05
     objeto
    -0.05
     instances
    -0.05
     -
    -0.05
     فيما
    -0.05
     macroeconomic
    -0.05
     स्ट्रीमिंग
    -0.05
    POSITIVE LOGITS
    skilled
    0.06
     länger
    0.06
     wiped
    0.06
     hailed
    0.06
     செய்தனர்
    0.06
     oi
    0.06
    ATION
    0.06
    เข้าใจ
    0.06
    rupted
    0.06
     vårt
    0.06
    Activations Density 0.002%

    No Known Activations