© 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. 118159
    Prev
    Next
    INDEX
    Explanations

    "

    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
    いろいろ
    -0.07
     ..,
    -0.06
     হন্ড
    -0.06
     Name
    -0.06
     !,
    -0.06
    ।,
    -0.06
     MANY
    -0.06
    。,
    -0.06
    ucionales
    -0.06
    చ
    -0.06
    POSITIVE LOGITS
     Beneficial
    0.06
    꽁
    0.06
     incorporation
    0.06
    痺
    0.06
    aily
    0.05
     experienced
    0.05
     acknowledges
    0.05
     introdu
    0.05
    ys
    0.05
     כאשר
    0.05
    Activations Density 0.004%

    No Known Activations