© 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. 129402
    Prev
    Next
    INDEX
    Explanations

    javascript selector syntax

    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
    인가
    -0.06
     más
    -0.06
    As
    -0.06
     верну
    -0.06
    Are
    -0.05
     referenced
    -0.05
    dí
    -0.05
    ふ
    -0.05
    Featuring
    -0.05
     special
    -0.05
    POSITIVE LOGITS
     şimdi
    0.06
     now
    0.06
     nyní
    0.06
     теперь
    0.06
    ﻰ
    0.06
     Şimdi
    0.06
     tantos
    0.06
    䂝
    0.06
     however
    0.06
    omatik
    0.06
    Activations Density 0.017%

    No Known Activations