© 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. 130206
    Prev
    Next
    INDEX
    Explanations

    declarative expressions

    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
     quotes
    -0.06
     IMMEDIATE
    -0.06
     trois
    -0.06
     herhangi
    -0.06
     drei
    -0.05
     twee
    -0.05
    ட்டின்
    -0.05
     প্রদেশের
    -0.05
     jederzeit
    -0.05
    <h3>
    -0.05
    POSITIVE LOGITS
     Lifecycle
    0.07
     scrutiny
    0.07
     compliance
    0.06
     scrutinized
    0.06
    衡量
    0.06
     ক্যাল
    0.06
     underneath
    0.06
     evaluated
    0.06
     timeframe
    0.06
     Confront
    0.06
    Activations Density 0.006%

    No Known Activations