© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 463
    Prev
    Next
    INDEX
    Explanations

    anything I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    𝘣
    1.76
    ার
    1.73
    然後
    1.72
    Если
    1.71
    Дан
    1.66
    দের
    1.62
    р
    1.57
    já
    1.55
    𝘬
    1.54
    সকল
    1.54
    POSITIVE LOGITS
     else
    2.40
    c
    1.82
    د
    1.82
    يات
    1.76
     amiss
    1.74
    ली
    1.73
    که
    1.69
    ment
    1.68
     spac
    1.64
    পত্রের
    1.58
    Activations Density 0.907%

    No Known Activations