© 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. 2107
    Prev
    Next
    INDEX
    Explanations

    instructions, questions, and solutions

    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
     non
    0.99
     been
    0.90
     not
    0.83
     voted
    0.82
     defunct
    0.81
     slightly
    0.80
     I
    0.80
     paying
    0.78
     D
    0.77
     staunch
    0.76
    POSITIVE LOGITS
    циям
    1.05
     दिरहम
    1.04
    Usuario
    1.01
    dą
    1.00
    цію
    0.99
    ikannya
    0.98
    şam
    0.97
    ávat
    0.97
    uminação
    0.96
    Therates
    0.96
    Activations Density 0.082%

    No Known Activations