© 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. 224446
    Prev
    Next
    INDEX
    Explanations

    HTTP or Google Account

    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
    ᖕ
    0.43
    シェル
    0.40
     ඔවුන්
    0.40
    亅
    0.39
    ysł
    0.39
    拒绝
    0.38
     مە
    0.38
    ঞ্জেল
    0.38
     Им
    0.38
    腈
    0.38
    POSITIVE LOGITS
     firsthand
    0.44
     last
    0.43
     desperation
    0.39
     lze
    0.39
    Bri
    0.39
     poč
    0.38
     Alfa
    0.38
     alku
    0.37
     can
    0.36
     erratic
    0.36
    Activations Density 0.000%

    No Known Activations