© 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. 128808
    Prev
    Next
    INDEX
    Explanations

    specifications and technical details

    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
     dianggap
    -0.06
    噪
    -0.06
     সাদা
    -0.06
     orthon
    -0.06
     shiny
    -0.06
     مر
    -0.06
     onscreen
    -0.06
    証
    -0.06
     Moreau
    -0.06
    RGBA
    -0.06
    POSITIVE LOGITS
    தாவது
    0.07
     ఇటీవల
    0.06
     систе
    0.06
     相关
    0.06
    レコード
    0.06
     pressurized
    0.06
     again
    0.06
    igable
    0.06
     Recorded
    0.06
     Pflanzen
    0.06
    Activations Density 0.006%

    No Known Activations