Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 19009
    Prev
    Next
    INDEX
    Explanations

    Google apps and settings

    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
     wrink
    0.43
    呂
    0.42
    INY
    0.41
     olacaktır
    0.40
    宮城県
    0.40
     landfall
    0.39
    rosse
    0.39
    TagName
    0.39
     elevar
    0.38
    簟
    0.38
    POSITIVE LOGITS
     apps
    0.70
     Apps
    0.62
    apps
    0.55
     앱
    0.55
    アプリ
    0.51
    Apps
    0.50
     Google
    0.50
     WebView
    0.49
    Google
    0.47
     ऐप्स
    0.44
    Activations Density 0.013%

    No Known Activations