© 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. 129189
    Prev
    Next
    INDEX
    Explanations

    molecular cloning and expression

    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
     yorum
    -0.08
     undocumented
    -0.06
     surpre
    -0.06
    OK
    -0.06
    }^{\
    -0.06
    तंत्र
    -0.06
    exclusions
    -0.06
    yh
    -0.06
    मंत्री
    -0.06
     are
    -0.06
    POSITIVE LOGITS
    在我们
    0.06
     glassware
    0.06
     vuonna
    0.06
    Adri
    0.06
    他にも
    0.06
     eki
    0.06
    enzo
    0.06
    定量
    0.06
    FBSDKApp
    0.06
    逛
    0.06
    Activations Density 0.003%

    No Known Activations