© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8874
    Prev
    Next
    INDEX
    Explanations

    compulsive addictive obsessive behaviors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    設計
    0.48
    筁
    0.40
     Дж
    0.39
     enlightened
    0.39
     gracefully
    0.38
     hoisting
    0.38
    UARY
    0.38
    冤
    0.38
    いい
    0.38
     headwinds
    0.38
    POSITIVE LOGITS
     compulsive
    0.80
     obses
    0.78
     obsessive
    0.74
     addictive
    0.68
     compuls
    0.67
     obsess
    0.66
     unconsciously
    0.66
     compensatory
    0.65
     addictions
    0.64
     Addiction
    0.62
    Activations Density 0.261%

    No Known Activations