© 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. 116216
    Prev
    Next
    INDEX
    Explanations

    contact the Office of Congressional Affairs

    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
     डिजाइन
    -0.06
     पुन्हा
    -0.06
     beloved
    -0.06
     predominant
    -0.06
     predominantly
    -0.06
     своей
    -0.06
     कॅम्प
    -0.06
     predomin
    -0.06
     primarily
    -0.06
     ചെയ്യുന്നത്
    -0.06
    POSITIVE LOGITS
    Published
    0.06
     ≠
    0.06
     /-
    0.06
    ⏭
    0.06
    गो
    0.06
    বীন্দ্র
    0.05
     यज्ञ
    0.05
    ^+,
    0.05
     있기
    0.05
    들이
    0.05
    Activations Density 0.004%

    No Known Activations