© 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. 119851
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
    ো
    -0.06
    没错
    -0.06
     narrow
    -0.06
     boasts
    -0.06
    中でも
    -0.06
    おすすめです
    -0.06
     involuntary
    -0.06
     включая
    -0.06
     जाहिर
    -0.06
     dividing
    -0.06
    POSITIVE LOGITS
     at
    0.07
     на
    0.06
    が
    0.06
     dans
    0.06
     on
    0.06
    scientists
    0.06
     такой
    0.06
    文字列
    0.06
     novos
    0.06
     in
    0.06
    Activations Density 0.003%

    No Known Activations