© 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. 128511
    Prev
    Next
    INDEX
    Explanations

    standards and criteria

    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
     будут
    -0.06
     domaine
    -0.06
     admittance
    -0.06
    芷
    -0.06
     nemen
    -0.06
     guarantee
    -0.06
     domaines
    -0.06
     depending
    -0.06
    给人
    -0.06
    *
    -0.06
    POSITIVE LOGITS
     newest
    0.06
     or
    0.06
     as
    0.06
     hela
    0.06
     dile
    0.06
    ఖ
    0.06
    ensuche
    0.05
    searchValue
    0.05
     powsta
    0.05
    城区
    0.05
    Activations Density 0.001%

    No Known Activations