© 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. 130409
    Prev
    Next
    INDEX
    Explanations

    free peoples, assist, good deeds

    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
     when
    -0.07
    เมื่อ
    -0.07
    最初の
    -0.07
    आरओ
    -0.07
     especial
    -0.06
    successful
    -0.06
    卻
    -0.06
    bagian
    -0.06
     bagian
    -0.06
    缺少
    -0.06
    POSITIVE LOGITS
     contemplating
    0.06
     tussen
    0.06
     possam
    0.06
     actualmente
    0.06
     cały
    0.06
     здесь
    0.06
     currently
    0.06
     nowy
    0.05
     sadness
    0.05
     seluruh
    0.05
    Activations Density 0.007%

    No Known Activations