© 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. 128458
    Prev
    Next
    INDEX
    Explanations

    infiltration into surrounding tissues

    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
     tarix
    -0.06
    通常
    -0.06
    或许
    -0.06
     generalmente
    -0.06
     সফরে
    -0.06
     efter
    -0.06
     spurred
    -0.06
    你有
    -0.06
     通常
    -0.06
     aquellos
    -0.06
    POSITIVE LOGITS
     part
    0.07
     Saying
    0.06
     also
    0.06
     ransom
    0.06
    附属
    0.06
     anche
    0.06
     used
    0.05
     Pulmonary
    0.05
     deft
    0.05
     двига
    0.05
    Activations Density 0.016%

    No Known Activations