© 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. 116470
    Prev
    Next
    INDEX
    Explanations

    time ranges and deadlines

    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
     samt
    -0.08
     तुरंत
    -0.06
     चाहता
    -0.06
     hemen
    -0.06
    足够
    -0.06
     immediate
    -0.06
    ID
    -0.06
     অতি
    -0.06
     imedi
    -0.06
    instant
    -0.06
    POSITIVE LOGITS
     storied
    0.08
    Honestly
    0.07
     consistently
    0.07
     previsão
    0.07
     прогно
    0.07
     allgemein
    0.07
     کہنا
    0.06
     predict
    0.06
    承诺
    0.06
     acabar
    0.06
    Activations Density 0.002%

    No Known Activations