© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130065
    Prev
    Next
    INDEX
    Explanations

    dates with months

    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
     verwendeten
    -0.07
     ”,
    -0.07
     với
    -0.07
     toegang
    -0.06
    に入
    -0.06
     suchen
    -0.06
     меня
    -0.06
     들어가
    -0.06
     ওয়েবসাইটে
    -0.06
     उन्हें
    -0.06
    POSITIVE LOGITS
     several
    0.07
    several
    0.07
     하루
    0.07
    two
    0.06
     ঈদের
    0.06
    Several
    0.06
     ইহার
    0.06
    fortunate
    0.06
    Two
    0.06
     just
    0.06
    Activations Density 0.008%

    No Known Activations