© 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. 120294
    Prev
    Next
    INDEX
    Explanations

    citations following names

    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
    /
    -0.08
    (
    -0.07
     not
    -0.07
    :
    -0.07
    ,
    -0.06
     is
    -0.06
     ከፍተኛ
    -0.06
     high
    -0.06
    c
    -0.06
    :-
    -0.06
    POSITIVE LOGITS
     آن
    0.07
     ilgili
    0.06
     coalition
    0.06
     टॉपर
    0.06
    ‌ها
    0.06
     ไป
    0.06
     مرتبط
    0.06
     tiga
    0.06
    즈
    0.06
    そういう
    0.06
    Activations Density 0.002%

    No Known Activations