© 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. 119155
    Prev
    Next
    INDEX
    Explanations

    telling or informing someone

    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
     also
    -0.09
    の一部
    -0.07
    also
    -0.06
     was
    -0.06
    是由
    -0.06
    䖝
    -0.06
    ത്തിയ
    -0.06
     defensor
    -0.06
    塩
    -0.06
     fosters
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.06
    জনিত
    0.06
    ↵↵↵↵
    0.06
    <0xE3>
    0.06
     саны
    0.05
    :
    0.05
    0.05
     тот
    0.05
     sucesivamente
    0.05
    我
    0.05
    Activations Density 0.021%

    No Known Activations