© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129321
    Prev
    Next
    INDEX
    Explanations

    autocrine, paracrine, secretion

    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
     how
    -0.06
    aka
    -0.06
     ſh
    -0.05
     Such
    -0.05
     aka
    -0.05
     επικ
    -0.05
    anum
    -0.05
     म्हणजेच
    -0.05
     pleasures
    -0.05
     आंतर
    -0.05
    POSITIVE LOGITS
     приложений
    0.06
     peaches
    0.06
     የሚ
    0.06
    meteor
    0.06
     conceivably
    0.06
     इत
    0.06
    
    0.06
    শংস
    0.06
     Persever
    0.06
     typographical
    0.06
    Activations Density 0.004%

    No Known Activations