© 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. 130071
    Prev
    Next
    INDEX
    Explanations

    variable followed by parenthesis

    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
    বর্তমান
    -0.06
    可怕
    -0.06
    했던
    -0.06
     whiche
    -0.06
     Fian
    -0.06
     seeming
    -0.06
     where
    -0.06
                        
    -0.06
    placeholder
    -0.06
     बनाया
    -0.06
    POSITIVE LOGITS
     variants
    0.06
    ids
    0.06
     یکی
    0.06
     ब्रांड
    0.06
     konk
    0.06
     it
    0.06
    Data
    0.06
     אחת
    0.05
    প্রণ
    0.05
     وم
    0.05
    Activations Density 0.002%

    No Known Activations