© 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. 116165
    Prev
    Next
    INDEX
    Explanations

    shall have / shall not

    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
    (
    -0.06
     টিক্কা
    -0.05
    interno
    -0.05
    स्थापित
    -0.05
     রাজশ
    -0.05
    esen
    -0.05
    新的
    -0.05
    tale
    -0.05
    tis
    -0.05
     even
    -0.05
    POSITIVE LOGITS
     was
    0.09
     only
    0.08
     also
    0.08
     jedoch
    0.08
     zawsze
    0.08
     had
    0.08
     лишь
    0.08
     недалеко
    0.07
     always
    0.07
     While
    0.07
    Activations Density 0.001%

    No Known Activations