© 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. 117239
    Prev
    Next
    INDEX
    Explanations

    misperception, or mistaken identification

    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
    決め
    -0.06
    ますが
    -0.06
    espoir
    -0.06
    referenced
    -0.06
    reserved
    -0.06
    xxxxx
    -0.06
    .....
    -0.06
    .........
    -0.05
     parking
    -0.05
     experts
    -0.05
    POSITIVE LOGITS
     perceived
    0.07
     percib
    0.06
     erroneously
    0.06
     Франции
    0.06
     mistaken
    0.06
     cotidiana
    0.06
     migratory
    0.06
     이를
    0.06
    誤
    0.06
    keto
    0.06
    Activations Density 0.049%

    No Known Activations