© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118921
    Prev
    Next
    INDEX
    Explanations

    names, abbreviations, dates, numbers, and sentence starters

    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
     are
    -0.07
     will
    -0.06
     of
    -0.06
     for
    -0.06
    stp
    -0.05
     drinker
    -0.05
     barg
    -0.05
     Batu
    -0.05
     from
    -0.05
     acutely
    -0.05
    POSITIVE LOGITS
     également
    0.08
    latest
    0.08
    也是
    0.08
     latest
    0.08
     também
    0.08
    昨天
    0.08
    También
    0.07
     mime
    0.07
    Latest
    0.07
     కూడా
    0.07
    Activations Density 0.009%

    No Known Activations