© 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. 118544
    Prev
    Next
    INDEX
    Explanations

    middle

    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
     wówczas
    -0.08
     returned
    -0.07
    ॉज
    -0.06
     château
    -0.06
    returns
    -0.06
     sucht
    -0.06
     верну
    -0.06
     returning
    -0.06
     ру
    -0.06
     anf
    -0.06
    POSITIVE LOGITS
    jewelry
    0.06
     optimization
    0.05
    可能
    0.05
    ಾಂ
    0.05
     demarc
    0.05
     interpretive
    0.05
     শরীর
    0.05
     hash
    0.05
    HASH
    0.05
     vstup
    0.05
    Activations Density 0.042%

    No Known Activations