© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118703
    Prev
    Next
    INDEX
    Explanations

    timeframes and durations

    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
     immediately
    -0.08
     сразу
    -0.08
     instantly
    -0.07
     odmah
    -0.07
    immediately
    -0.07
     immedi
    -0.07
     inmediato
    -0.06
     Immediately
    -0.06
     immediate
    -0.06
     immédi
    -0.06
    POSITIVE LOGITS
     knowledge
    0.07
    NOWLEDGE
    0.07
     വില
    0.06
     zbog
    0.06
     sostit
    0.06
     Physic
    0.06
    Knowledge
    0.06
     Epub
    0.06
     nhằm
    0.06
    Virus
    0.06
    Activations Density 0.009%

    No Known Activations