© 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. 120550
    Prev
    Next
    INDEX
    Explanations

    types of any

    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
     including
    -0.07
    存在する
    -0.06
    bao
    -0.06
     innehåller
    -0.06
    Including
    -0.06
    給你
    -0.06
    たち
    -0.06
     Including
    -0.06
    িক্স
    -0.06
    mine
    -0.06
    POSITIVE LOGITS
     April
    0.07
     oui
    0.06
     AGRE
    0.06
     italiana
    0.06
     использовании
    0.06
     kantor
    0.06
     δύο
    0.06
     Австра
    0.06
     julho
    0.06
     shrewd
    0.06
    Activations Density 0.003%

    No Known Activations