© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119063
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
     on
    -0.07
     (
    -0.07
    .
    -0.07
     این
    -0.07
     この
    -0.06
     when
    -0.06
     در
    -0.06
    देवा
    -0.06
     تغییر
    -0.06
     это
    -0.06
    POSITIVE LOGITS
     granular
    0.08
    EARCH
    0.07
     and
    0.06
    在新
    0.06
    granular
    0.06
     patterns
    0.06
     capucha
    0.06
    パターン
    0.06
     iconic
    0.06
     foothills
    0.06
    Activations Density 0.002%

    No Known Activations