© 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. 128678
    Prev
    Next
    INDEX
    Explanations

    scheduling and naming processes

    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
     having
    -0.07
     což
    -0.07
     विक्रम
    -0.06
     experimentation
    -0.06
     imaginative
    -0.06
     Metrics
    -0.06
     innovation
    -0.06
     innovative
    -0.06
     absent
    -0.06
    ђено
    -0.06
    POSITIVE LOGITS
     üzerinden
    0.06
     zmieni
    0.06
    忿
    0.06
    等级
    0.06
     sett
    0.06
     приорите
    0.06
     destes
    0.06
     그룹
    0.06
    associations
    0.05
     competir
    0.05
    Activations Density 0.001%

    No Known Activations