© 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. 129557
    Prev
    Next
    INDEX
    Explanations

    credentials, clearance, require, transfer

    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
     marx
    -0.06
     inten
    -0.05
     wav
    -0.05
     ActionListener
    -0.05
     확률
    -0.05
     formative
    -0.05
    Flipper
    -0.05
     بارے
    -0.05
    वणे
    -0.05
    στη
    -0.05
    POSITIVE LOGITS
     Credentials
    0.07
     clearance
    0.07
     commuting
    0.06
    arantine
    0.06
     Costume
    0.06
     requiring
    0.06
     cargo
    0.06
    require
    0.06
    transfer
    0.06
     Clearance
    0.06
    Activations Density 0.003%

    No Known Activations