© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130087
    Prev
    Next
    INDEX
    Explanations

    code delimiters and surrounding words

    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
     также
    -0.08
     also
    -0.08
     também
    -0.07
     cannot
    -0.07
     또한
    -0.07
     también
    -0.07
     також
    -0.07
    नेहा
    -0.07
     ainda
    -0.07
    都不是
    -0.07
    POSITIVE LOGITS
     pribli
    0.07
     примерно
    0.07
     and
    0.07
     khoảng
    0.06
    がありますが
    0.06
     ලබා
    0.06
     aproximadamente
    0.06
    約
    0.06
     vaid
    0.06
     ungefähr
    0.06
    Activations Density 0.009%

    No Known Activations