© 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. 119804
    Prev
    Next
    INDEX
    Explanations

    Ben Lomond

    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
    าท
    -0.07
    以上に
    -0.06
     هذه
    -0.06
    ⇐
    -0.06
    보다
    -0.06
    oció
    -0.06
     Boca
    -0.06
    ンダ
    -0.06
     premio
    -0.06
    درسة
    -0.06
    POSITIVE LOGITS
     статус
    0.07
    和
    0.06
     godly
    0.06
     mush
    0.06
     تاثیر
    0.05
     সুরে
    0.05
    dain
    0.05
    各
    0.05
     পঞ্চাশ
    0.05
     selectively
    0.05
    Activations Density 0.001%

    No Known Activations