© 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. 119443
    Prev
    Next
    INDEX
    Explanations

    variable assignments and data definitions

    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
    と同じ
    -0.06
    等の
    -0.06
     tüm
    -0.06
     which
    -0.06
     nao
    -0.05
     lätt
    -0.05
     time
    -0.05
     et
    -0.05
     donde
    -0.05
    hiya
    -0.05
    POSITIVE LOGITS
     vaikka
    0.07
     તો
    0.06
     multimedia
    0.06
     এতটা
    0.06
    reflectionCamera
    0.06
     तो
    0.06
     notwithstanding
    0.06
    例えば
    0.06
     సాహిత
    0.06
    aunque
    0.06
    Activations Density 0.006%

    No Known Activations