© 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. 128982
    Prev
    Next
    INDEX
    Explanations

    use or application to something

    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
     new
    -0.06
     അനുവദ
    -0.06
     මෙම
    -0.06
     กับ
    -0.06
     valamint
    -0.06
    ただ
    -0.06
     sadece
    -0.06
     आठ
    -0.06
     тільки
    -0.06
    ನ
    -0.06
    POSITIVE LOGITS
    don
    0.06
     wonderfully
    0.06
     we
    0.06
     observations
    0.06
    eyeglasses
    0.06
     specifica
    0.06
    িত্র
    0.05
    muy
    0.05
    屋さん
    0.05
    May
    0.05
    Activations Density 0.011%

    No Known Activations