© 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. 15645
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas or newlines

    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
    en
    0.85
     reckons
    0.79
    eries
    0.78
    iis
    0.78
    eeee
    0.78
     실
    0.77
    codigo
    0.76
    sé
    0.76
    nish
    0.75
    GetComponents
    0.74
    POSITIVE LOGITS
    Complaint
    0.86
     cite
    0.85
    khov
    0.85
    ায়া
    0.82
    ය
    0.82
    ्यूम
    0.81
     चौथ
    0.81
     Oxf
    0.79
    ATP
    0.77
     Grundlage
    0.77
    Activations Density 0.026%

    No Known Activations