© 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. 206
    Prev
    Next
    INDEX
    Explanations

    violence hotline

    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
    taining
    1.16
     luxurious
    1.10
    tains
    1.07
     ότι
    1.02
     treacherous
    0.96
     heels
    0.95
    %!
    0.94
    驃
    0.93
     the
    0.91
     heterogeneous
    0.91
    POSITIVE LOGITS
    Наи
    1.00
     খাঁর
    0.91
    ímetros
    0.91
    Centered
    0.88
    uniqueItems
    0.86
    Poland
    0.86
     पर्
    0.84
    └
    0.83
     huyện
    0.83
    ˗
    0.82
    Activations Density 1.015%

    No Known Activations