© 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. 118835
    Prev
    Next
    INDEX
    Explanations

    boolean type indicator

    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
     Widers
    -0.07
    nope
    -0.06
     overestimate
    -0.06
    рифмети
    -0.06
     Nope
    -0.06
    ઞ
    -0.06
     änd
    -0.06
    Ꮽ
    -0.06
     پزشکی
    -0.06
     выражение
    -0.05
    POSITIVE LOGITS
     which
    0.07
     alors
    0.07
     now
    0.07
    then
    0.06
     Alors
    0.06
     with
    0.06
     Waz
    0.06
     distinction
    0.06
     지금
    0.06
     perceptible
    0.06
    Activations Density 0.001%

    No Known Activations