© 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. 191346
    Prev
    Next
    INDEX
    Explanations

    drying and towels

    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
    傕
    0.44
    Shower
    0.43
    𒂠
    0.42
    Dav
    0.42
     thịt
    0.40
    કો
    0.40
     Whatsapp
    0.40
    禛
    0.40
     WhatsApp
    0.39
    SendMessage
    0.39
    POSITIVE LOGITS
    clothes
    0.50
    Clothes
    0.40
    cluse
    0.39
     towel
    0.39
     belongings
    0.39
    urus
    0.38
     clothes
    0.38
     dryer
    0.38
     paraphernalia
    0.37
     towels
    0.37
    Activations Density 0.002%

    No Known Activations