© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118039
    Prev
    Next
    INDEX
    Explanations

    precious metals and compounds

    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
     boric
    -0.06
    funktionen
    -0.06
    killed
    -0.06
    Executive
    -0.06
     주변
    -0.06
     morte
    -0.06
    Emotional
    -0.06
     Emotional
    -0.06
     nhắc
    -0.05
     родствен
    -0.05
    POSITIVE LOGITS
     опу
    0.07
    ('\
    0.06
     CLLocation
    0.06
     нако
    0.06
     costly
    0.06
    㽞
    0.06
    hatiti
    0.06
     Butcher
    0.06
     begins
    0.06
    "/>
    0.06
    Activations Density 0.014%

    No Known Activations