© 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. 120032
    Prev
    Next
    INDEX
    Explanations

    technical code and terms

    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
     своему
    -0.06
    noticed
    -0.06
     cosm
    -0.06
     Ο
    -0.05
    צא
    -0.05
     noticed
    -0.05
    ιλ
    -0.05
     కృ
    -0.05
     samoz
    -0.05
     electrochemical
    -0.05
    POSITIVE LOGITS
    pportune
    0.07
     tangents
    0.07
     countering
    0.06
     ಅದೇ
    0.06
     ভারতে
    0.06
    避け
    0.06
     urgente
    0.06
     wives
    0.06
     feasible
    0.06
     얘는
    0.06
    Activations Density 0.001%

    No Known Activations