© 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. 129460
    Prev
    Next
    INDEX
    Explanations

    months and periods

    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
     extraordinary
    -0.06
     Potential
    -0.05
    ్రహ్
    -0.05
    candidate
    -0.05
    particular
    -0.05
    redit
    -0.05
    Local
    -0.05
    ইয়া
    -0.05
     copyrighted
    -0.05
    indd
    -0.05
    POSITIVE LOGITS
     Monaten
    0.08
     месяцев
    0.07
     weeks
    0.07
     sulla
    0.07
     months
    0.07
     অতিথ
    0.07
    悵
    0.07
     pueden
    0.07
     meses
    0.07
     месяц
    0.07
    Activations Density 0.014%

    No Known Activations