© 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. 118601
    Prev
    Next
    INDEX
    Explanations

    information and settings

    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
     each
    -0.06
    自宅
    -0.06
     अपलोड
    -0.06
    成年
    -0.06
     ऑडियो
    -0.06
     karbon
    -0.06
    源
    -0.06
     donor
    -0.06
     hvert
    -0.06
    episode
    -0.06
    POSITIVE LOGITS
     information
    0.08
    设置
    0.07
     Informationen
    0.07
     información
    0.06
    情報を
    0.06
    情報
    0.06
     blinds
    0.06
     UITextField
    0.06
     정보
    0.06
    information
    0.06
    Activations Density 0.002%

    No Known Activations