© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130959
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and code elements

    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
    8
    -0.06
    <strong>
    -0.06
    https
    -0.06
     زبان
    -0.06
    とても
    -0.05
    4
    -0.05
     exposing
    -0.05
    <i>
    -0.05
     компетен
    -0.05
    映射
    -0.05
    POSITIVE LOGITS
     cuz
    0.06
    ತ್ರೆ
    0.06
     erstwhile
    0.06
     преж
    0.06
     reinforcements
    0.06
     ochron
    0.06
    <unused72>
    0.06
    igel
    0.06
    डॉ
    0.06
     därför
    0.06
    Activations Density 0.003%

    No Known Activations