© 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. 17-GEMMASCOPE-2-RES-16K
    7. 11050
    Prev
    Next
    INDEX
    Explanations

    recent performance, developments, or studies

    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_17_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
    া
    2.54
    на
    2.49
     personnes
    2.28
     schließlich
    2.25
    ة
    2.25
    ্লাহ
    2.16
    ড
    2.12
    ை
    2.10
     bisogna
    2.09
    း
    2.07
    POSITIVE LOGITS
     spate
    2.95
    ম
    2.26
     Dadurch
    2.12
     flurry
    2.09
    elijk
    1.96
    fulness
    1.87
     diri
    1.83
    र
    1.80
    екси
    1.79
     uptick
    1.76
    Activations Density 0.026%

    No Known Activations