© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130977
    Prev
    Next
    INDEX
    Explanations

    developing articles, code triggers

    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
    bu
    -0.07
     (
    -0.06
    e
    -0.06
    (
    -0.05
    is
    -0.05
     being
    -0.05
    aw
    -0.05
    I
    -0.05
    ah
    -0.05
    Sh
    -0.05
    POSITIVE LOGITS
     дуже
    0.09
     bardzo
    0.09
     intestino
    0.08
     nagyon
    0.08
     extremamente
    0.08
     ogrom
    0.08
    Hydrochloride
    0.08
     usando
    0.08
     cuando
    0.08
     очень
    0.08
    Activations Density 0.001%

    No Known Activations