© 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. 130934
    Prev
    Next
    INDEX
    Explanations

    code comments and symbols

    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
    ကြီး
    -0.06
    (
    -0.06
     within
    -0.06
    :
    -0.05
    *:
    -0.05
    ’:
    -0.05
    naam
    -0.05
     larger
    -0.05
    something
    -0.05
     bigger
    -0.05
    POSITIVE LOGITS
    ᠴ
    0.06
     भी
    0.06
     også
    0.06
     selanjutnya
    0.06
     மற்றும்
    0.06
     टेक
    0.06
     أيضًا
    0.06
     እና
    0.06
     również
    0.06
     and
    0.06
    Activations Density 0.001%

    No Known Activations