© 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. 116679
    Prev
    Next
    INDEX
    Explanations

    regardless of

    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
     even
    -0.08
     même
    -0.07
     név
    -0.07
     bahkan
    -0.07
     даже
    -0.07
     bezieht
    -0.07
    Anche
    -0.07
     anche
    -0.07
    だけでも
    -0.07
     även
    -0.06
    POSITIVE LOGITS
    ESOME
    0.05
    awesome
    0.05
     Faso
    0.05
     pokuš
    0.05
     kuitenkin
    0.05
    不了
    0.05
     வழிப
    0.05
    眝
    0.05
     runway
    0.05
     மாறி
    0.05
    Activations Density 0.011%

    No Known Activations