© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83641
    Prev
    Next
    INDEX
    Explanations

    drugs of abuse and dependence

    np_acts-logits-general · gemini-2.5-flash-lite

    words and phrases related to drug abuse, addiction, and psychoactive substances.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     polio
    -0.93
    ょ
    -0.93
     subconsciously
    -0.85
     Testo
    -0.84
     Noida
    -0.84
    utri
    -0.83
    amenta
    -0.83
     данном
    -0.82
    alyse
    -0.82
     durant
    -0.80
    POSITIVE LOGITS
     users
    1.34
     street
    1.07
     Users
    0.98
     user
    0.94
     Street
    0.93
    streets
    0.92
     dependence
    0.89
     contextos
    0.88
    Street
    0.87
    UserDto
    0.86
    Activations Density 0.071%

    No Known Activations