© 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. 120583
    Prev
    Next
    INDEX
    Explanations

    file paths and locations

    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
     jednym
    -0.08
    ført
    -0.06
     одного
    -0.06
     Hôm
    -0.06
    秪
    -0.06
     одним
    -0.06
     invari
    -0.06
     hôm
    -0.06
     of
    -0.06
     கமல்
    -0.06
    POSITIVE LOGITS
     tentativo
    0.08
     attempts
    0.06
    attempt
    0.06
     nicest
    0.06
     تلاش
    0.06
     attempt
    0.06
    this
    0.06
     payment
    0.06
    copy
    0.06
    நக
    0.06
    Activations Density 0.023%

    No Known Activations