© 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. 129464
    Prev
    Next
    INDEX
    Explanations

    certain specific existing

    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
     هسه
    -0.07
    orene
    -0.06
     harsher
    -0.06
     raref
    -0.06
     Magnesium
    -0.06
     vyn
    -0.05
     storied
    -0.05
    cA
    -0.05
    োজেন
    -0.05
     Vorteil
    -0.05
    POSITIVE LOGITS
     bestimmte
    0.08
     bepaalde
    0.07
    existing
    0.07
     on
    0.07
     bestimmten
    0.06
     certain
    0.06
     existentes
    0.06
     with
    0.06
     dengan
    0.06
    在上
    0.06
    Activations Density 0.001%

    No Known Activations