© 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. 130721
    Prev
    Next
    INDEX
    Explanations

    storyline plot twists narrative

    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
    다른
    -0.06
     vzh
    -0.05
     veya
    -0.05
    他
    -0.05
    рядок
    -0.05
    ظهر
    -0.05
     odpowied
    -0.05
     beliau
    -0.05
     அவர்
    -0.05
    深圳
    -0.05
    POSITIVE LOGITS
     whatever
    0.07
     eloquently
    0.07
     laughable
    0.06
     idiot
    0.06
     pointless
    0.06
     ежеднев
    0.06
     killings
    0.06
     idiots
    0.06
     Occ
    0.06
     defam
    0.06
    Activations Density 0.005%

    No Known Activations