© 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. 119364
    Prev
    Next
    INDEX
    Explanations

    acknowledging existing

    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
     viele
    -0.07
     rapporter
    -0.07
     wielu
    -0.06
     or
    -0.06
     profund
    -0.06
     visant
    -0.06
    долго
    -0.06
     или
    -0.06
     conclusion
    -0.06
    Many
    -0.06
    POSITIVE LOGITS
    cknowled
    0.06
    ("")]
    0.06
    เพื่อให้
    0.06
     použí
    0.06
     existing
    0.06
     त्यावर
    0.06
    Acknowled
    0.06
     enhance
    0.06
    ใช้
    0.06
    すぐに
    0.06
    Activations Density 0.001%

    No Known Activations