© 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. 116874
    Prev
    Next
    INDEX
    Explanations

    navigation back to previous sections

    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
     waarom
    -0.06
     why
    -0.06
     আপনার
    -0.06
    Inicial
    -0.06
     kanilang
    -0.06
     their
    -0.06
     identifik
    -0.06
    plicate
    -0.06
    為什麼
    -0.06
    있
    -0.06
    POSITIVE LOGITS
     возвра
    0.07
     terug
    0.07
     вернуться
    0.06
     visits
    0.06
     tilbake
    0.06
    via
    0.06
    return
    0.06
     correspondences
    0.06
    กลับ
    0.06
     journeys
    0.06
    Activations Density 0.014%

    No Known Activations