© 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. 120105
    Prev
    Next
    INDEX
    Explanations

    citations and identifiers

    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
     asp
    -0.07
     okolo
    -0.06
     inconceivable
    -0.06
    Officers
    -0.06
     halinde
    -0.06
     hundreds
    -0.06
    最初
    -0.06
     considered
    -0.06
    osterol
    -0.05
    处理
    -0.05
    POSITIVE LOGITS
     proprio
    0.07
     scenarios
    0.06
     demographic
    0.06
    ectonic
    0.06
     kidnap
    0.06
     कर्तव्यों
    0.06
    standalone
    0.06
     demographics
    0.06
     updates
    0.06
    activo
    0.06
    Activations Density 0.003%

    No Known Activations