© 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. 119575
    Prev
    Next
    INDEX
    Explanations

    quantifiable characteristics

    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
     फ्रॉम
    -0.07
     from
    -0.07
     från
    -0.06
     लहान
    -0.06
    ダー
    -0.06
     mecan
    -0.06
     reunited
    -0.06
    ëren
    -0.06
     ενός
    -0.06
     द्वारा
    -0.06
    POSITIVE LOGITS
     all
    0.06
    ┤
    0.06
     noteworthy
    0.06
     it
    0.06
     overt
    0.06
    Ps
    0.06
     meu
    0.06
    В
    0.05
    ations
    0.05
     буди
    0.05
    Activations Density 0.007%

    No Known Activations