© 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. 120166
    Prev
    Next
    INDEX
    Explanations

    sequences of degrees

    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
    may
    -0.06
     should
    -0.06
     airways
    -0.05
    should
    -0.05
     always
    -0.05
     Department
    -0.05
     ہتھیار
    -0.05
    IEC
    -0.05
    தியின்
    -0.05
    ör
    -0.05
    POSITIVE LOGITS
     hatta
    0.06
     paradigms
    0.06
    给我们
    0.06
    蝓
    0.06
    viles
    0.06
    ちょうど
    0.06
    有
    0.06
    我們
    0.06
     แต่
    0.06
     mensuales
    0.06
    Activations Density 0.001%

    No Known Activations