© 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. 128406
    Prev
    Next
    INDEX
    Explanations

    variation and variability

    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
     different
    -0.10
     разные
    -0.09
     distintas
    -0.09
     διαφορε
    -0.08
     différente
    -0.08
     diferente
    -0.08
     വ്യത്യസ്ത
    -0.08
    不同的
    -0.08
     diferite
    -0.08
     diferentes
    -0.08
    POSITIVE LOGITS
     PROP
    0.06
    pository
    0.06
    に加え
    0.06
     Occupation
    0.06
    khart
    0.06
     INVEST
    0.06
     forthwith
    0.05
    赶紧
    0.05
    HAND
    0.05
    があれば
    0.05
    Activations Density 0.022%

    No Known Activations