© 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. 117716
    Prev
    Next
    INDEX
    Explanations

    hidden / secret / concealed

    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
     maintains
    -0.07
     иденти
    -0.06
     după
    -0.06
     plafond
    -0.06
     flushing
    -0.06
     maintaining
    -0.06
     maintained
    -0.06
     following
    -0.06
     поддержа
    -0.06
    identical
    -0.06
    POSITIVE LOGITS
    hidden
    0.08
     secretive
    0.07
    隱
    0.07
    悄
    0.07
    隐
    0.07
    隠
    0.06
     Hidden
    0.06
     secrecy
    0.06
    éricas
    0.06
    Hidden
    0.06
    Activations Density 0.049%

    No Known Activations