© 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. 116175
    Prev
    Next
    INDEX
    Explanations

    .pone

    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
    ),
    -0.08
     такі
    -0.07
    様な
    -0.07
     such
    -0.07
     ),
    -0.06
     Vedanta
    -0.06
    nan
    -0.06
    background
    -0.06
     такой
    -0.06
     таким
    -0.06
    POSITIVE LOGITS
     shrank
    0.07
     conventional
    0.07
     experimented
    0.07
     avaient
    0.06
     shrunk
    0.06
     combines
    0.06
     était
    0.06
     expériment
    0.06
     отличается
    0.06
    Combine
    0.06
    Activations Density 0.002%

    No Known Activations