© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120502
    Prev
    Next
    INDEX
    Explanations

    instead, rather, plutôt

    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
     crema
    -0.06
     زمانی
    -0.06
    propertyName
    -0.06
     proposed
    -0.06
    proposed
    -0.06
     bassist
    -0.06
     எனது
    -0.06
     adaptar
    -0.06
     entsprechenden
    -0.06
     degenerate
    -0.06
    POSITIVE LOGITS
     instead
    0.07
     ench
    0.06
    Instead
    0.06
     Creek
    0.06
     piuttosto
    0.06
     plutôt
    0.06
     rather
    0.06
    牟
    0.06
     Instead
    0.06
     జ్ఞాప
    0.06
    Activations Density 0.001%

    No Known Activations