© 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. 130333
    Prev
    Next
    INDEX
    Explanations

    code punctuation and structure

    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
    Reuters
    -0.06
    Res
    -0.06
     secondhand
    -0.06
    Then
    -0.05
    News
    -0.05
    speech
    -0.05
     समाचार
    -0.05
     Res
    -0.05
    ならラクマ
    -0.05
     গিয়েছিলাম
    -0.05
    POSITIVE LOGITS
     BJP
    0.07
     विपक्ष
    0.06
    PAssignment
    0.06
     decadent
    0.06
     luxurious
    0.06
     Hibernate
    0.06
     !}\
    0.06
     дни
    0.06
    嚴
    0.06
     Debian
    0.06
    Activations Density 0.003%

    No Known Activations