© 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. 129134
    Prev
    Next
    INDEX
    Explanations

    any, act, bond, system followed by class, video, or longer terms

    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
     tomonidan
    -0.07
    ρος
    -0.06
     moderator
    -0.06
     anos
    -0.06
     iniciativa
    -0.06
     conval
    -0.06
     Molina
    -0.06
     aonde
    -0.06
     विशिष्ट
    -0.06
     инициа
    -0.06
    POSITIVE LOGITS
     are
    0.07
     각각
    0.06
     seem
    0.06
    却没有
    0.06
    ℹ
    0.06
     is
    0.06
     Agricultural
    0.06
     seems
    0.06
     కూడా
    0.06
    Extra
    0.06
    Activations Density 0.002%

    No Known Activations