© 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. 130657
    Prev
    Next
    INDEX
    Explanations

    analysis, hypothesis, assessment

    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
     клини
    -0.09
     clinical
    -0.09
     மருத்துவ
    -0.09
     medical
    -0.09
     clinically
    -0.08
    临床
    -0.08
     clinician
    -0.08
     neuro
    -0.08
     медицин
    -0.08
     imaging
    -0.08
    POSITIVE LOGITS
     on
    0.07
     analiz
    0.07
     corporate
    0.07
     Corporate
    0.07
     على
    0.07
    analyse
    0.06
    financial
    0.06
     econometric
    0.06
     multilateral
    0.06
    hasht
    0.06
    Activations Density 0.011%

    No Known Activations