© 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. 129313
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    once
    -0.06
    Please
    -0.06
    If
    -0.06
    getClient
    -0.06
    کار
    -0.06
     wird
    -0.06
    കൊ
    -0.06
    When
    -0.06
    As
    -0.06
     outrage
    -0.06
    POSITIVE LOGITS
     routinely
    0.07
     femei
    0.06
     repeatable
    0.06
    🉑
    0.06
     ഹിന്ദു
    0.06
    小孩
    0.06
     immediatamente
    0.06
    …,
    0.06
    ્યાં
    0.06
     repeatability
    0.06
    Activations Density 0.001%

    No Known Activations