© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78749
    Prev
    Next
    INDEX
    Explanations

    classical conditioning and learned associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    menuBar
    -0.90
    の中から
    -0.80
     Borel
    -0.79
    Voting
    -0.75
    Халы
    -0.74
    parseFrom
    -0.72
    bestimmung
    -0.71
    ⋇
    -0.69
    ῃ
    -0.69
    Napoli
    -0.68
    POSITIVE LOGITS
     conditioning
    1.35
     conditioned
    1.29
    conditioned
    1.18
     Conditioning
    1.18
     pairing
    1.18
     CS
    1.13
     classical
    1.08
     Pavlov
    1.08
    conditioning
    1.06
     Classical
    1.05
    Activations Density 0.099%

    No Known Activations