© 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. 128939
    Prev
    Next
    INDEX
    Explanations

    disagreement or changing minds

    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
    GPS
    -0.06
    ructure
    -0.06
    cribed
    -0.06
     rive
    -0.06
     ग़
    -0.06
     поча
    -0.06
    வான்
    -0.06
     deceit
    -0.06
     ಆತ್ಮ
    -0.06
     intra
    -0.06
    POSITIVE LOGITS
     resistant
    0.08
    resistant
    0.07
    resolvers
    0.06
     தீர்
    0.06
     ModelAndView
    0.06
     resistente
    0.06
     remain
    0.06
    <u>
    0.05
     custo
    0.05
    事务
    0.05
    Activations Density 0.025%

    No Known Activations