© 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. 119855
    Prev
    Next
    INDEX
    Explanations

    dates and times (numbers, days, months, times, separators)

    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
     DIRECTIONS
    -0.07
     वास्तव
    -0.06
     realistically
    -0.06
     truly
    -0.06
     πραγμα
    -0.06
    真正
    -0.06
     has
    -0.06
     оправ
    -0.05
    合理的
    -0.05
     (-
    -0.05
    POSITIVE LOGITS
    :
    0.09
    เพราะ
    0.08
     because
    0.08
     porque
    0.08
     another
    0.08
     další
    0.08
     เพราะ
    0.07
    因为
    0.07
     क्योंकि
    0.07
     rápido
    0.07
    Activations Density 0.005%

    No Known Activations