© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 9562
    Prev
    Next
    INDEX
    Explanations

    and/or followed by outcome or state

    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
    τικής
    0.32
    反射
    0.28
    ﮭ
    0.27
    illes
    0.26
     định
    0.26
    渠道
    0.25
     enfim
    0.25
     disponibilidade
    0.25
     Zusammenhang
    0.24
    管理局
    0.24
    POSITIVE LOGITS
     Ў
    0.35
    ęk
    0.33
    িপুর
    0.33
     Warcraft
    0.33
    Jenis
    0.32
    برای
    0.32
    GYPT
    0.32
     holidays
    0.32
    €.
    0.31
    «.
    0.31
    Activations Density 0.131%

    No Known Activations