© 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. 120097
    Prev
    Next
    INDEX
    Explanations

    numbers and classifications

    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
     a
    -0.07
     de
    -0.07
    ,
    -0.07
     same
    -0.06
     changes
    -0.06
     Same
    -0.06
    ),
    -0.06
    same
    -0.06
    -
    -0.06
     включая
    -0.06
    POSITIVE LOGITS
     actuality
    0.08
     soooo
    0.07
     protože
    0.07
     chronology
    0.07
     steve
    0.06
     WITH
    0.06
    者を
    0.06
     paket
    0.06
     sooo
    0.06
    Because
    0.06
    Activations Density 0.001%

    No Known Activations