© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130626
    Prev
    Next
    INDEX
    Explanations

    starts with http://

    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
     vždy
    -0.06
     and
    -0.06
     et
    -0.06
     the
    -0.06
     Myth
    -0.06
     учетом
    -0.06
     নিজ
    -0.06
    의
    -0.06
    adding
    -0.06
     точки
    -0.06
    POSITIVE LOGITS
     которы
    0.07
     который
    0.06
    飘
    0.06
     Wired
    0.06
     raging
    0.06
     ursprünglich
    0.06
     hurtful
    0.06
    飄
    0.06
     bein
    0.06
     که
    0.06
    Activations Density 0.001%

    No Known Activations