© 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. 118327
    Prev
    Next
    INDEX
    Explanations

    includes with angle brackets

    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
     events
    -0.06
    郦
    -0.06
     particularly
    -0.06
     gas
    -0.06
     compete
    -0.06
     विरु
    -0.06
     حف
    -0.05
     David
    -0.05
     हार्ड
    -0.05
     gana
    -0.05
    POSITIVE LOGITS
    合计
    0.07
     большинство
    0.06
     다른
    0.06
    她在
    0.06
     ίδ
    0.06
     aquilo
    0.06
    Eleven
    0.06
     сосе
    0.06
    简洁
    0.06
    ፕሮ
    0.06
    Activations Density 0.001%

    No Known Activations