© 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. 128878
    Prev
    Next
    INDEX
    Explanations

    personal names and place names

    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
     Behavioral
    -0.06
     перший
    -0.06
     delightful
    -0.06
    fetching
    -0.06
     शर्ट
    -0.06
     احسن
    -0.06
    *****
    -0.06
     thoughtfulness
    -0.06
     fetching
    -0.06
     animación
    -0.06
    POSITIVE LOGITS
     названия
    0.09
     names
    0.08
     landmarks
    0.08
     Names
    0.07
     prefixes
    0.07
     powsta
    0.07
     name
    0.06
    名称
    0.06
     within
    0.06
     listop
    0.06
    Activations Density 0.009%

    No Known Activations