© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130155
    Prev
    Next
    INDEX
    Explanations

    of small

    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
     örne
    -0.06
     каждым
    -0.06
     যাত্র
    -0.06
     _;
    -0.06
     なら
    -0.06
    Persona
    -0.06
     sedangkan
    -0.06
     Mal
    -0.06
     trên
    -0.06
     tendrán
    -0.06
    POSITIVE LOGITS
     دلچ
    0.07
     due
    0.06
    That
    0.06
    Because
    0.06
     which
    0.06
    いい
    0.06
     دلیل
    0.06
    because
    0.06
    due
    0.06
     பல்வேறு
    0.06
    Activations Density 0.039%

    No Known Activations