© 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. 118890
    Prev
    Next
    INDEX
    Explanations

    datetime fields

    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
     даже
    -0.07
    稱為
    -0.07
     ακόμα
    -0.07
     vantagem
    -0.07
     naciones
    -0.07
    なんだ
    -0.07
     você
    -0.06
     també
    -0.06
     период
    -0.06
     ความ
    -0.06
    POSITIVE LOGITS
    always
    0.06
    ¶
    0.06
    🍒
    0.05
     আজকের
    0.05
    े
    0.05
     inhomogeneities
    0.05
    stit
    0.05
     while
    0.05
     totality
    0.05
    ט
    0.05
    Activations Density 0.004%

    No Known Activations