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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 15379
    Prev
    Next
    INDEX
    Explanations

    linking components or processes

    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
    मु
    0.48
     مهما
    0.39
    ع
    0.39
    regardless
    0.38
    unless
    0.37
    يس
    0.36
    罢
    0.36
    دست
    0.36
    ת
    0.36
    َة
    0.35
    POSITIVE LOGITS
     another
    0.58
     corresponding
    0.52
     aforementioned
    0.47
     ওই
    0.45
     nearby
    0.45
     this
    0.43
    前記
    0.43
     pairs
    0.43
     instances
    0.42
     an
    0.42
    Activations Density 0.015%

    No Known Activations