© 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. 128555
    Prev
    Next
    INDEX
    Explanations

    numbers, lists, figures

    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
     ostensibly
    -0.07
     iniziamo
    -0.07
     empezamos
    -0.07
    फरी
    -0.06
     originating
    -0.06
     /*
    -0.06
     tiny
    -0.06
    https
    -0.06
     expensive
    -0.06
     אך
    -0.06
    POSITIVE LOGITS
    芓
    0.06
    권을
    0.06
     Ford
    0.06
    streets
    0.06
     dans
    0.06
     streets
    0.06
    能够在
    0.06
     крайне
    0.06
     স্নাত
    0.05
     iris
    0.05
    Activations Density 0.001%

    No Known Activations