© 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. 118986
    Prev
    Next
    INDEX
    Explanations

    dialogue punctuation and starting words

    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
     Now
    -0.06
     amendments
    -0.06
     modernisation
    -0.06
     enggak
    -0.05
     সম্মিলিত
    -0.05
    ORIG
    -0.05
     nods
    -0.05
     argue
    -0.05
    normalized
    -0.05
     बतौर
    -0.05
    POSITIVE LOGITS
     всегда
    0.07
     завжди
    0.07
     selalu
    0.07
     zawsze
    0.07
     always
    0.07
    いつも
    0.07
     دائما
    0.07
     항상
    0.06
    Always
    0.06
     hill
    0.06
    Activations Density 0.014%

    No Known Activations