© 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. 118056
    Prev
    Next
    INDEX
    Explanations

    successful completion

    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
     by
    -0.07
     dring
    -0.06
     канал
    -0.06
     piping
    -0.06
     fury
    -0.06
    ▢
    -0.06
     forno
    -0.06
     unitarity
    -0.06
     requiring
    -0.06
    বর্তী
    -0.06
    POSITIVE LOGITS
    spers
    0.07
     gestellt
    0.06
     chuckled
    0.06
    CRE
    0.06
    hte
    0.06
     mesta
    0.06
     όπου
    0.05
     successfully
    0.05
     felicit
    0.05
     consultation
    0.05
    Activations Density 0.001%

    No Known Activations