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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17286
    Prev
    Next
    INDEX
    Explanations

    alcohol and wine

    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
    рите
    0.47
     ডেভেলপ
    0.46
     ஜனநாயக
    0.46
    灾
    0.44
     डेवलपमेंट
    0.44
     স্বপ্নের
    0.43
    Development
    0.43
     компьютер
    0.42
    ренных
    0.42
     Computational
    0.41
    POSITIVE LOGITS
     alcohol
    1.58
     alcoholic
    1.52
     алкого
    1.52
     drink
    1.49
     alkohol
    1.49
    🍺
    1.47
     drinks
    1.45
     alkoh
    1.45
    🍷
    1.45
    酒
    1.42
    Activations Density 0.106%

    No Known Activations