© 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. 119256
    Prev
    Next
    INDEX
    Explanations

    order and quantity

    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
     Speaking
    -0.06
    ković
    -0.06
     several
    -0.06
    Speaking
    -0.06
     Several
    -0.06
     заработной
    -0.06
     constraint
    -0.06
     glanced
    -0.06
     Constraint
    -0.06
    슌
    -0.05
    POSITIVE LOGITS
     علاقوں
    0.06
     অঞ্চলে
    0.06
     스토리
    0.06
    ামের
    0.06
    ান্ট
    0.06
     routinely
    0.06
     hills
    0.06
     नमी
    0.06
     naturali
    0.05
     kullan
    0.05
    Activations Density 0.002%

    No Known Activations