© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116014
    Prev
    Next
    INDEX
    Explanations

    presence of

    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
    Negative Logits
    igraphic
    -0.06
     transgress
    -0.06
    िक्ष
    -0.06
    тических
    -0.06
    icheskoj
    -0.06
    ख़
    -0.05
    armament
    -0.05
     التي
    -0.05
     τί
    -0.05
     തുടങ്ങ
    -0.05
    POSITIVE LOGITS
     第三
    0.06
     today
    0.06
     tredje
    0.06
    第二个
    0.06
    他又
    0.06
    多个
    0.06
    method
    0.06
     так
    0.06
     todays
    0.06
     secondo
    0.06
    Activations Density 0.022%

    No Known Activations