© 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. 129572
    Prev
    Next
    INDEX
    Explanations

    exclamations and interjections

    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
     that
    -0.07
     olyan
    -0.07
    oltre
    -0.06
     outweigh
    -0.06
     entire
    -0.06
     ሁለት
    -0.06
    兩
    -0.06
     주의
    -0.05
     is
    -0.05
     unforgettable
    -0.05
    POSITIVE LOGITS
    !,
    0.08
    Ꮷ
    0.06
    ovič
    0.06
    !;
    0.06
     !,
    0.06
    Actually
    0.06
    Douglas
    0.06
    (),
    0.06
    稍
    0.06
     চালা
    0.06
    Activations Density 0.005%

    No Known Activations