© 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. 129018
    Prev
    Next
    INDEX
    Explanations

    file extensions like xls, doc, mdb

    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
    爱好者
    -0.06
    embedded
    -0.06
    NEG
    -0.06
     chromospheric
    -0.06
     保
    -0.06
     NEG
    -0.06
     विराजमान
    -0.06
     অনলাইনে
    -0.06
    可以直接
    -0.05
     negatives
    -0.05
    POSITIVE LOGITS
     plusieurs
    0.07
    หลาย
    0.06
     molte
    0.06
     nhiều
    0.06
    ühlen
    0.06
     vários
    0.06
     molti
    0.06
     renal
    0.06
     periodic
    0.06
     several
    0.06
    Activations Density 0.010%

    No Known Activations