© 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. 118647
    Prev
    Next
    INDEX
    Explanations

    famous people's names

    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
     they
    -0.08
     charismatic
    -0.08
     creates
    -0.08
     achieve
    -0.07
     flamboyant
    -0.07
    Creating
    -0.07
     innovative
    -0.07
     створи
    -0.07
     Creating
    -0.07
     influential
    -0.07
    POSITIVE LOGITS
     muzik
    0.06
     кома
    0.06
     sente
    0.06
     on
    0.06
    ка
    0.06
    高志森
    0.06
     перева
    0.05
     मैं
    0.05
    marque
    0.05
     bila
    0.05
    Activations Density 0.013%

    No Known Activations