© 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. 116090
    Prev
    Next
    INDEX
    Explanations

    kill, Grand, Predict, Tag

    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
     często
    -0.06
    처럼
    -0.06
    特定の
    -0.06
     belirli
    -0.06
    与其他
    -0.06
     altre
    -0.06
     것처럼
    -0.06
     echelon
    -0.06
     born
    -0.06
     memilih
    -0.06
    POSITIVE LOGITS
     including
    0.07
     power
    0.07
    铌
    0.07
     poderia
    0.07
     Therefore
    0.07
    包括
    0.06
     incluyendo
    0.06
     could
    0.06
    algebra
    0.06
    including
    0.06
    Activations Density 0.002%

    No Known Activations