© 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. 119881
    Prev
    Next
    INDEX
    Explanations

    places to stay

    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
     해당
    -0.07
     successfully
    -0.06
    成功
    -0.06
    獲
    -0.06
     izango
    -0.06
    successfully
    -0.06
    IVIDUAL
    -0.06
     bluff
    -0.06
    meleri
    -0.06
     unsuccessfully
    -0.06
    POSITIVE LOGITS
    と思われる
    0.06
    小学校
    0.06
    FLOW
    0.06
     সামগ্র
    0.06
    lowski
    0.06
     submerged
    0.05
    шкин
    0.05
     organisme
    0.05
     Gifford
    0.05
    inclusive
    0.05
    Activations Density 0.005%

    No Known Activations