© 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. 120500
    Prev
    Next
    INDEX
    Explanations

    numeric or code prefixes

    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
     significant
    -0.06
    низ
    -0.06
     appalling
    -0.06
     lakukan
    -0.06
    וּ
    -0.06
    ﮑ
    -0.06
    preferably
    -0.06
     அல்லது
    -0.06
     appalled
    -0.06
     preferably
    -0.06
    POSITIVE LOGITS
    some
    0.07
     some
    0.06
    不是
    0.06
     unele
    0.06
     teljes
    0.06
     restaurant
    0.06
     някои
    0.06
    Some
    0.06
    之前
    0.05
    so
    0.05
    Activations Density 0.001%

    No Known Activations