© 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. 117275
    Prev
    Next
    INDEX
    Explanations

    job offers

    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
     Negoti
    -0.09
    Negoti
    -0.08
     negotiation
    -0.08
     Negotiation
    -0.08
    negoti
    -0.08
     negotiations
    -0.08
     negotiable
    -0.08
     negociación
    -0.07
    谈判
    -0.07
     negoti
    -0.07
    POSITIVE LOGITS
     holding
    0.06
     ব্যবহার
    0.05
    ব্যবহার
    0.05
    system
    0.05
     occupying
    0.05
    rod
    0.05
     käyttö
    0.05
    ded
    0.05
    好了
    0.05
    ȝ
    0.05
    Activations Density 0.047%

    No Known Activations