© 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. 128356
    Prev
    Next
    INDEX
    Explanations

    beta-blockers and adrenergic receptors

    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
     research
    -0.06
     expenditure
    -0.06
     budgetary
    -0.06
     dépenses
    -0.06
    Research
    -0.06
     RESEARCH
    -0.06
     expenditures
    -0.06
    費
    -0.06
     একদিন
    -0.06
    midnight
    -0.06
    POSITIVE LOGITS
     forestry
    0.08
     forest
    0.07
     calming
    0.07
     Forestry
    0.07
     automóviles
    0.07
     silky
    0.07
    forest
    0.06
    숲
    0.06
     frightening
    0.06
     forested
    0.06
    Activations Density 0.028%

    No Known Activations