© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116544
    Prev
    Next
    INDEX
    Explanations

    manufacturing processes

    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
    utage
    -0.05
    ಂದ್ರ
    -0.05
     согласно
    -0.05
     underage
    -0.05
    كلمنا
    -0.05
     ஜூ
    -0.05
    ees
    -0.05
     уро
    -0.05
    ロット
    -0.05
    uzo
    -0.05
    POSITIVE LOGITS
    アクセサリー
    0.07
     Bangalore
    0.06
    争议
    0.06
     putern
    0.06
     wewnętr
    0.06
     גע
    0.06
     যাবতীয়
    0.06
    此外
    0.06
    akti
    0.06
     चलती
    0.06
    Activations Density 0.011%

    No Known Activations