© 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. 130712
    Prev
    Next
    INDEX
    Explanations

    file is part of

    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
     менен
    -0.07
    HI
    -0.06
    बत
    -0.06
    Hi
    -0.05
    就會
    -0.05
    㕩
    -0.05
     મોટી
    -0.05
    多多
    -0.05
    ът
    -0.05
     wereld
    -0.05
    POSITIVE LOGITS
     simple
    0.07
     more
    0.07
    ₁(
    0.07
     simplistic
    0.07
    нила
    0.06
     noviembre
    0.06
     November
    0.06
     two
    0.06
     one
    0.06
     foolproof
    0.06
    Activations Density 0.003%

    No Known Activations