© 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. 128719
    Prev
    Next
    INDEX
    Explanations

    partial or incomplete

    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
     कुछ
    -0.08
     ಸ್ವಲ್ಪ
    -0.07
     setelah
    -0.07
     niektórych
    -0.07
     некоторые
    -0.06
     after
    -0.06
     sparingly
    -0.06
     ചില
    -0.06
     can
    -0.06
     ninth
    -0.06
    POSITIVE LOGITS
     ہمیشہ
    0.06
     znal
    0.06
     ricordo
    0.06
     always
    0.06
     alltid
    0.06
    洲
    0.06
    mers
    0.06
     any
    0.06
     erneut
    0.06
    专业的
    0.06
    Activations Density 0.015%

    No Known Activations