© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120235
    Prev
    Next
    INDEX
    Explanations

    copyright notices or attributions

    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
    因为它
    -0.06
    yed
    -0.06
     Cic
    -0.05
     DE
    -0.05
    和
    -0.05
     committing
    -0.05
     :).
    -0.05
    alternative
    -0.05
    by
    -0.05
    embang
    -0.05
    POSITIVE LOGITS
     он
    0.09
     для
    0.08
     for
    0.08
     لهذه
    0.07
     только
    0.07
     ему
    0.07
     тільки
    0.07
    ங்களுக்கு
    0.06
     исключительно
    0.06
     to
    0.06
    Activations Density 0.006%

    No Known Activations