© 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. 119579
    Prev
    Next
    INDEX
    Explanations

    magnitude components

    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
     však
    -0.06
     without
    -0.06
    舊
    -0.06
     однако
    -0.06
    を使った
    -0.05
     bug
    -0.05
     instant
    -0.05
    Detected
    -0.05
     okol
    -0.05
    without
    -0.05
    POSITIVE LOGITS
    ネイル
    0.06
     भैया
    0.06
     grids
    0.06
     adore
    0.06
     تصميم
    0.06
    北美
    0.06
    少女
    0.05
     FLY
    0.05
    gged
    0.05
    बीसी
    0.05
    Activations Density 0.001%

    No Known Activations