© 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. 120336
    Prev
    Next
    INDEX
    Explanations

    Base excess

    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
    際に
    -0.06
    下的
    -0.06
    際には
    -0.06
    Write
    -0.06
     Write
    -0.06
     that
    -0.06
     ！
    -0.06
     সঙ্গে
    -0.05
     কী
    -0.05
    সাথে
    -0.05
    POSITIVE LOGITS
    وانه
    0.07
    proposal
    0.06
     astăzi
    0.06
     giggle
    0.06
     rupam
    0.06
     spout
    0.06
     molded
    0.06
     zapro
    0.06
     countertop
    0.06
     proposta
    0.06
    Activations Density 0.005%

    No Known Activations