© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 119945
    Prev
    Next
    INDEX
    Explanations

    arrow connections

    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_16_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
    k
    0.59
     channeled
    0.54
    ೊಳ
    0.52
     кон
    0.52
     burner
    0.52
    kách
    0.52
    ę
    0.52
     ос
    0.51
     ойнотуу
    0.51
     curled
    0.51
    POSITIVE LOGITS
    주
    0.60
    鍝
    0.54
    Hipp
    0.53
    Juan
    0.52
    Star
    0.51
    AKS
    0.51
    Mango
    0.50
    原创
    0.50
    แก้ไข
    0.49
    Victoria
    0.47
    Activations Density 0.000%

    No Known Activations