© 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. 120555
    Prev
    Next
    INDEX
    Explanations

    Id, PrimaryKey, JsonProperty

    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
     svoju
    -0.07
     vividly
    -0.06
     hapless
    -0.06
     सत्यापित
    -0.06
    這位
    -0.06
     comprehensively
    -0.06
     genauso
    -0.06
    جوم
    -0.06
     promotes
    -0.06
    这位
    -0.06
    POSITIVE LOGITS
    Ī
    0.07
    Ia
    0.06
    į
    0.06
     East
    0.06
    ☘
    0.05
    ń
    0.05
    ជាង
    0.05
     Ia
    0.05
     ئێ
    0.05
    णातील
    0.05
    Activations Density 0.002%

    No Known Activations