© 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. 119494
    Prev
    Next
    INDEX
    Explanations

    court or abstract titles

    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
    ですが
    -0.07
    both
    -0.07
     αλλά
    -0.06
     large
    -0.06
     but
    -0.06
     Suprema
    -0.06
     strikingly
    -0.06
    Converting
    -0.06
     प्रकोष्ठ
    -0.06
    🖱
    -0.06
    POSITIVE LOGITS
     ১৪
    0.06
     graciously
    0.06
     конструкция
    0.06
     joins
    0.05
     purchased
    0.05
     চাপের
    0.05
     wa
    0.05
     သည်
    0.05
     pareja
    0.05
     this
    0.05
    Activations Density 0.001%

    No Known Activations