© 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-262K
    7. 10723
    Prev
    Next
    INDEX
    Explanations

    cannabis, CBD, and hemp

    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_262k_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
    ającym
    0.44
     ogrod
    0.43
    ającą
    0.43
    potato
    0.42
    umac
    0.42
    薯
    0.42
    ellung
    0.41
    Potato
    0.41
    水源
    0.41
    庫
    0.41
    POSITIVE LOGITS
     CBD
    0.89
    CBD
    0.72
     cbd
    0.63
     Cbd
    0.63
     CBN
    0.56
    cbd
    0.52
     anxiety
    0.50
     CB
    0.49
     hemp
    0.48
     cannab
    0.48
    Activations Density 0.017%

    No Known Activations