© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120726
    Prev
    Next
    INDEX
    Explanations

    medical learning and instruction

    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
     wants
    -0.07
     Like
    -0.07
     here
    -0.07
     Extremely
    -0.06
     안에
    -0.06
     becoming
    -0.06
     like
    -0.06
     school
    -0.06
     you
    -0.06
     what
    -0.06
    POSITIVE LOGITS
     symposium
    0.07
     informative
    0.07
    に行った
    0.07
     cranial
    0.06
     manoeuvre
    0.06
     précis
    0.06
     elicited
    0.06
     informar
    0.06
     ziyaret
    0.06
     Noël
    0.06
    Activations Density 0.011%

    No Known Activations