© 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. 117936
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

    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
     기다
    -0.08
     بعض
    -0.07
     wichtig
    -0.07
     చాలా
    -0.07
     บาง
    -0.07
     lehetős
    -0.07
     майже
    -0.07
    ногда
    -0.07
     फंस
    -0.07
     πρώτη
    -0.07
    POSITIVE LOGITS
    )
    0.06
     easily
    0.06
    ,
    0.06
    ;
    0.06
    these
    0.06
    are
    0.06
    kom
    0.06
    correspond
    0.05
    ins
    0.05
     these
    0.05
    Activations Density 0.004%

    No Known Activations