© 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. 129225
    Prev
    Next
    INDEX
    Explanations

    code blocks with hyphens and underscores

    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
     અન્ય
    -0.08
     предыду
    -0.07
     so
    -0.07
     inade
    -0.07
     다른
    -0.07
    其它
    -0.07
     pued
    -0.07
     нынеш
    -0.06
     інших
    -0.06
     other
    -0.06
    POSITIVE LOGITS
     k
    0.06
     天
    0.06
    because
    0.06
     گزار
    0.06
     David
    0.06
    というのは
    0.06
     Stephen
    0.05
     realizar
    0.05
    ल्फी
    0.05
     Peter
    0.05
    Activations Density 0.004%

    No Known Activations