© 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. 118752
    Prev
    Next
    INDEX
    Explanations

    in the presence of solvent

    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
    횟
    -0.07
     pristine
    -0.06
    ıyordu
    -0.06
    そのため
    -0.06
     Bris
    -0.06
    twice
    -0.06
     그래서
    -0.06
     richer
    -0.06
    metal
    -0.06
    agel
    -0.06
    POSITIVE LOGITS
     Hippo
    0.06
     at
    0.06
     name
    0.06
    过
    0.06
     answers
    0.06
     answer
    0.05
    ดำเนินการ
    0.05
    采取
    0.05
    первых
    0.05
     недоста
    0.05
    Activations Density 0.010%

    No Known Activations