© 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. 6007
    Prev
    Next
    INDEX
    Explanations

    email addresses and security contacts

    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
    通话
    0.46
     cramps
    0.45
     blobs
    0.42
     undersea
    0.41
    cular
    0.41
     autobi
    0.41
    🤌
    0.40
    RawO
    0.39
    bilical
    0.39
    ,-\
    0.39
    POSITIVE LOGITS
     email
    1.66
     Email
    1.52
    email
    1.47
    Email
    1.34
    邮箱
    1.33
     ईमेल
    1.30
     EMAIL
    1.27
     emailing
    1.25
     contact
    1.20
    mailto
    1.20
    Activations Density 0.020%

    No Known Activations