© 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. 119241
    Prev
    Next
    INDEX
    Explanations

    discuss appointment with

    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
     roundtable
    -0.08
     conference
    -0.08
     конферен
    -0.07
     참석
    -0.07
     konfer
    -0.07
     конференции
    -0.07
     행사
    -0.07
     conférence
    -0.07
     attendee
    -0.07
     ณ
    -0.07
    POSITIVE LOGITS
     to
    0.06
    で作
    0.06
    Maker
    0.06
     mainstream
    0.06
    已
    0.06
    budget
    0.05
    💕
    0.05
     இந்
    0.05
    也
    0.05
     come
    0.05
    Activations Density 0.014%

    No Known Activations