© 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. 129799
    Prev
    Next
    INDEX
    Explanations

    academic articles and lectures

    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
     όπου
    -0.07
     where
    -0.06
    在哪里
    -0.06
     whose
    -0.06
     واقعہ
    -0.06
     حيث
    -0.06
     transaction
    -0.06
     donde
    -0.06
    Mve
    -0.06
     Tallahassee
    -0.06
    POSITIVE LOGITS
    製造
    0.06
    制造
    0.06
    戚
    0.06
    があるので
    0.06
    𝕒
    0.06
    ଷ
    0.06
     Қ
    0.05
    加速度
    0.05
     제가
    0.05
     हिर
    0.05
    Activations Density 0.045%

    No Known Activations