© 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. 128652
    Prev
    Next
    INDEX
    Explanations

    "or" or "and" followed by punctuation

    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
     सात
    -0.07
     нашего
    -0.06
     naš
    -0.06
     nostro
    -0.06
     revived
    -0.06
     Entretanto
    -0.06
     accentuated
    -0.06
     exclusivity
    -0.06
    Peter
    -0.06
     sekä
    -0.06
    POSITIVE LOGITS
     to
    0.07
     mga
    0.06
     today
    0.06
     you
    0.06
    <strong>
    0.06
     on
    0.06
     поэтому
    0.06
     with
    0.06
     offerings
    0.06
     sehingga
    0.06
    Activations Density 0.032%

    No Known Activations