© 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. 116221
    Prev
    Next
    INDEX
    Explanations

    game titles and topics

    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
     may
    -0.06
    目前
    -0.06
     полага
    -0.06
    atform
    -0.06
     좀
    -0.06
     によ
    -0.06
     wakes
    -0.06
    hourly
    -0.06
     szerint
    -0.06
     చెందిన
    -0.05
    POSITIVE LOGITS
     enchanting
    0.07
    幸せ
    0.07
     Control
    0.06
     관리
    0.06
     행복
    0.06
    easy
    0.06
     cherry
    0.06
     elementary
    0.06
     zákaz
    0.06
     managing
    0.06
    Activations Density 0.005%

    No Known Activations