© 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. 45524
    Prev
    Next
    INDEX
    Explanations

    substance use, abuse, and dependence

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

    references to substance use, abuse, and addiction.

    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
     veiks
    -0.88
    Reduc
    -0.80
     operasi
    -0.77
     vienas
    -0.77
    Mathieu
    -0.76
    mentação
    -0.75
    YOUTUBE
    -0.74
     recipient
    -0.73
    ult
    -0.73
    anueva
    -0.73
    POSITIVE LOGITS
     abuse
    2.09
     Abuse
    1.64
     misuse
    1.35
    abuse
    1.34
     abuso
    1.27
    Abuse
    1.27
     use
    1.18
     abusing
    1.16
     abused
    1.12
     dependence
    1.08
    Activations Density 0.050%

    No Known Activations