© 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. 116974
    Prev
    Next
    INDEX
    Explanations

    place names and counts

    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
    于
    -0.07
     or
    -0.06
     дни
    -0.06
    ിത്ര
    -0.06
    Concerning
    -0.05
     forecast
    -0.05
    ㄱ
    -0.05
    ような
    -0.05
     varsa
    -0.05
    运用
    -0.05
    POSITIVE LOGITS
     pissed
    0.06
     nasty
    0.06
     slightly
    0.06
    slightly
    0.06
     остальных
    0.06
    有一定的
    0.06
     запад
    0.06
     nagyon
    0.06
     Slightly
    0.06
     OTHER
    0.06
    Activations Density 0.001%

    No Known Activations