© 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. 129226
    Prev
    Next
    INDEX
    Explanations

    cat

    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
     本当
    -0.06
     آسیب
    -0.06
    َم
    -0.06
    நீங்கள்
    -0.06
     mortals
    -0.06
     большую
    -0.05
     अभ्यास
    -0.05
     दक्षिण
    -0.05
     זמן
    -0.05
     described
    -0.05
    POSITIVE LOGITS
     Seja
    0.07
    矜
    0.06
    =
    0.06
     سواء
    0.06
    ın
    0.06
    hafte
    0.06
     perte
    0.06
     nossos
    0.05
     सैनिकों
    0.05
     takes
    0.05
    Activations Density 0.001%

    No Known Activations