© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12750
    Prev
    Next
    INDEX
    Explanations

    Germany, individual accountability, organizations, Stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_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
    ⋮
    0.88
    ς
    0.86
    acide
    0.79
    Clause
    0.79
    rawberry
    0.78
    oser
    0.77
    ijiet
    0.77
    ﾝ
    0.76
    re
    0.75
    sama
    0.75
    POSITIVE LOGITS
    並沒有
    0.67
    أي
    0.66
     apasion
    0.66
     updatedAt
    0.65
     scrutiny
    0.61
    詣
    0.60
    沒有
    0.59
     положения
    0.59
    '.
    0.59
     يقول
    0.59
    Activations Density 0.001%

    No Known Activations