© 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. 128931
    Prev
    Next
    INDEX
    Explanations

    highest placed or charting

    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
     born
    -0.06
    之前
    -0.06
    meier
    -0.06
    বৎ
    -0.06
     -
    -0.06
     செய்யும்
    -0.05
     begun
    -0.05
     bb
    -0.05
    eh
    -0.05
    dew
    -0.05
    POSITIVE LOGITS
     حوزه
    0.06
     istek
    0.06
     an
    0.06
     ∗
    0.06
    ಾಗಿದೆ
    0.06
    aspid
    0.06
     coração
    0.06
     diminution
    0.06
     Currently
    0.06
    ገ
    0.06
    Activations Density 0.010%

    No Known Activations