© 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. 129223
    Prev
    Next
    INDEX
    Explanations

    "impression" "(", "Login" "("

    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
     it
    -0.06
    ()
    -0.06
    他
    -0.06
     нале
    -0.06
    It
    -0.06
     его
    -0.06
    下面的
    -0.05
    来看
    -0.05
     परे
    -0.05
    So
    -0.05
    POSITIVE LOGITS
     Når
    0.09
     noteworthy
    0.08
     når
    0.07
    quando
    0.07
    Quando
    0.07
     когда
    0.07
     Quando
    0.07
     klassischen
    0.07
     audacious
    0.07
     også
    0.07
    Activations Density 0.003%

    No Known Activations