© 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. 111489
    Prev
    Next
    INDEX
    Explanations

    $ followed by variables

    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
     schrift
    0.37
    失
    0.37
    移
    0.37
    emit
    0.36
    нього
    0.34
    e
    0.34
    フト
    0.33
     than
    0.33
     emitting
    0.33
    視
    0.33
    POSITIVE LOGITS
    数据集
    0.47
     डॉल
    0.46
    чери
    0.45
     ૧
    0.43
     huyện
    0.42
     DataSet
    0.42
    いただきました
    0.41
    तावनी
    0.41
    铁路
    0.41
    Debbie
    0.41
    Activations Density 0.000%

    No Known Activations