© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 8006
    Prev
    Next
    INDEX
    Explanations

    fashion trends, accessories, victim

    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_40_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
     Radio
    0.40
    wc
    0.40
    纷
    0.39
    charger
    0.39
    taxes
    0.39
     radio
    0.38
     taxes
    0.38
    iles
    0.37
     Hansen
    0.36
     Driver
    0.36
    POSITIVE LOGITS
    ista
    0.78
    istas
    0.73
    ISTA
    0.65
     trends
    0.57
    潮流
    0.57
    👗
    0.56
     fashion
    0.56
     аксессу
    0.55
     ट्रेंड
    0.54
     ファッション
    0.54
    Activations Density 0.002%

    No Known Activations