© 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. 117335
    Prev
    Next
    INDEX
    Explanations

    react-native-meteor iOS

    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
    acted
    -0.06
     如果
    -0.06
     they
    -0.06
    their
    -0.06
    واع
    -0.06
     rechts
    -0.06
     Если
    -0.06
     BEFORE
    -0.06
     three
    -0.06
    POSITIVE LOGITS
     прида
    0.07
     весьма
    0.06
     at
    0.06
     emphasised
    0.06
     คง
    0.06
     χρει
    0.06
     emphasise
    0.05
    ুত
    0.05
    Faction
    0.05
     bastante
    0.05
    Activations Density 0.024%

    No Known Activations