© 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. 29595
    Prev
    Next
    INDEX
    Explanations

    data fetching

    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
     排
    0.45
    video
    0.40
    illust
    0.39
     آئ
    0.39
     Regulation
    0.38
     سخت
    0.38
     新
    0.37
    gul
    0.37
    hard
    0.37
     있어
    0.37
    POSITIVE LOGITS
     conventionally
    0.48
     otherwise
    0.44
     cheaply
    0.44
     technologically
    0.42
     citiz
    0.41
     টাইমস
    0.40
     decently
    0.40
    </h6>
    0.39
     rêve
    0.39
    وهات
    0.39
    Activations Density 0.000%

    No Known Activations