© 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. 119811
    Prev
    Next
    INDEX
    Explanations

    Grid or DataGridView context

    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
    自分が
    -0.07
    All
    -0.06
    First
    -0.06
     diversified
    -0.06
     степен
    -0.06
    自己
    -0.06
     worldwide
    -0.06
     собра
    -0.06
    眾
    -0.06
     First
    -0.06
    POSITIVE LOGITS
     પાણી
    0.08
     ৭
    0.07
     on
    0.06
     bicarbonate
    0.06
     на
    0.06
     mods
    0.06
     modifications
    0.06
     på
    0.06
     ওয়েবসাইটে
    0.06
     mudança
    0.06
    Activations Density 0.007%

    No Known Activations