© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118246
    Prev
    Next
    INDEX
    Explanations

    time indicators

    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
    relaxation
    -0.06
    Also
    -0.06
    didn
    -0.06
     didn
    -0.06
     Also
    -0.06
     Aka
    -0.06
    ㎜
    -0.06
    also
    -0.06
     enforcing
    -0.06
     relaxation
    -0.06
    POSITIVE LOGITS
     до
    0.08
     jetzt
    0.07
     désormais
    0.07
     now
    0.07
     nyní
    0.07
    เพื่อ
    0.07
    への
    0.06
     तक
    0.06
     следующих
    0.06
     weitere
    0.06
    Activations Density 0.003%

    No Known Activations