© 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. 118534
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

    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
     their
    -0.07
     där
    -0.06
    ・・・
    -0.06
    their
    -0.06
     freely
    -0.06
     more
    -0.06
    从而
    -0.06
     obtenue
    -0.06
     where
    -0.06
     three
    -0.06
    POSITIVE LOGITS
    可是
    0.06
    ภาษ
    0.06
     directives
    0.06
     nörd
    0.06
     capacidades
    0.06
    掌控
    0.06
     zuk
    0.06
     erud
    0.05
     supplementing
    0.05
    CONTROL
    0.05
    Activations Density 0.001%

    No Known Activations