© 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. 120641
    Prev
    Next
    INDEX
    Explanations

    probability, algebra, Association, Thursday, Q

    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
    の一部
    -0.07
     সম্মত
    -0.07
     পর্বত
    -0.07
     CLLocation
    -0.07
     apesar
    -0.07
     Turismo
    -0.06
     scrollTo
    -0.06
     আন্দোলন
    -0.06
    Localization
    -0.06
     문서
    -0.06
    POSITIVE LOGITS
     sophisticated
    0.06
     blond
    0.06
    iseur
    0.06
     prized
    0.06
     Ramsey
    0.06
     जबरदस्त
    0.06
     mighty
    0.05
     amazing
    0.05
     glowing
    0.05
    سن
    0.05
    Activations Density 0.005%

    No Known Activations