© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 21167
    Prev
    Next
    INDEX
    Explanations

    cloud providers: AWS, Azure, GCP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     laatste
    0.77
     attham
    0.66
     lancéolées
    0.60
    <unused385>
    0.60
     anciennes
    0.59
     sabato
    0.59
     vecchio
    0.59
    getRedTeam
    0.59
     richied
    0.58
     unresponsive
    0.58
    POSITIVE LOGITS
    id
    0.71
    AWS
    0.70
    in
    0.68
     AWS
    0.66
    ח
    0.65
    is
    0.64
    0
    0.64
    Azure
    0.59
    {
    0.59
    fl
    0.57
    Activations Density 0.143%

    No Known Activations