© 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. 22-GEMMASCOPE-RES-131K
    7. 70538
    Prev
    Next
    INDEX
    Explanations

    addiction and dependency disorders

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

    content related to addiction, substance abuse, and dependency disorders.

    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_22/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
    e
    -1.36
    愜
    -1.22
     the
    -1.18
    f
    -1.09
    ūs
    -1.06
    n
    -1.05
    I
    -1.05
    ふん
    -1.05
     tausend
    -1.04
    面具
    -1.04
    POSITIVE LOGITS
     Może
    1.43
     Kiedy
    1.41
    宴会
    1.41
    ないけど
    1.38
     Američ
    1.37
     Pokud
    1.34
     camuf
    1.34
     Canadá
    1.34
     helicóptero
    1.34
    当事
    1.33
    Activations Density 0.071%

    No Known Activations