© 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. 116629
    Prev
    Next
    INDEX
    Explanations

    end time measurement

    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
     in
    -0.06
     dei
    -0.06
     thách
    -0.06
     मजाक
    -0.06
    នៅក្នុង
    -0.06
     empfohlen
    -0.06
    ็บ
    -0.06
     inoltre
    -0.05
     tempus
    -0.05
    発送
    -0.05
    POSITIVE LOGITS
     трех
    0.06
    극
    0.06
    luğu
    0.06
     трёх
    0.06
     ثلاث
    0.06
    гром
    0.06
     his
    0.06
    luğ
    0.06
    荨
    0.06
     bero
    0.06
    Activations Density 0.001%

    No Known Activations