© 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. 129440
    Prev
    Next
    INDEX
    Explanations

    numerical values and units

    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
     more
    -0.08
    更为
    -0.06
    upar
    -0.06
     adına
    -0.06
     bardziej
    -0.06
     πιο
    -0.06
    先天
    -0.06
    ⁰
    -0.06
    inträ
    -0.06
     más
    -0.06
    POSITIVE LOGITS
     tiež
    0.06
    Totals
    0.06
    的总
    0.06
    gressive
    0.06
     also
    0.06
     কারনে
    0.06
     accumulate
    0.06
     strives
    0.06
     tambien
    0.06
     often
    0.05
    Activations Density 0.010%

    No Known Activations