© 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. 118242
    Prev
    Next
    INDEX
    Explanations

    digits often followed by punctuation

    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
    yczy
    -0.06
    ..,
    -0.06
    することも
    -0.06
    FY
    -0.06
     가능
    -0.06
    皑
    -0.06
     transitive
    -0.06
     transitional
    -0.06
    ...,
    -0.06
    厉
    -0.06
    POSITIVE LOGITS
     الم
    0.06
     Poole
    0.06
     م
    0.06
     wieder
    0.06
     bờ
    0.06
    లో
    0.06
     como
    0.06
     erő
    0.05
     است
    0.05
     د
    0.05
    Activations Density 0.005%

    No Known Activations