© 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. 130029
    Prev
    Next
    INDEX
    Explanations

    sports scores and events

    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
    According
    -0.07
     According
    -0.06
     Anwendung
    -0.06
     sangat
    -0.06
     गैस
    -0.06
     formally
    -0.06
     Minuten
    -0.06
     Formal
    -0.05
     लगभग
    -0.05
     thrown
    -0.05
    POSITIVE LOGITS
     pokrač
    0.07
     increment
    0.07
     termasuk
    0.06
     increments
    0.06
     denominator
    0.06
    前に
    0.06
     etcétera
    0.06
     zwięks
    0.06
     ഉൾ
    0.06
     идут
    0.06
    Activations Density 0.003%

    No Known Activations