© 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. 118938
    Prev
    Next
    INDEX
    Explanations

    types of categories

    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
    既存
    -0.06
    示
    -0.06
     natürlichen
    -0.06
    他の
    -0.06
     уверен
    -0.05
     sorprend
    -0.05
     будут
    -0.05
     другой
    -0.05
     Algorithms
    -0.05
     좋을
    -0.05
    POSITIVE LOGITS
    类型
    0.07
     type
    0.07
     تباہ
    0.06
    getType
    0.06
    type
    0.06
    類型
    0.06
     it
    0.06
     வருகிறது
    0.06
     TYPE
    0.06
    controls
    0.06
    Activations Density 0.016%

    No Known Activations