© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 142102
    Prev
    Next
    INDEX
    Explanations

    Medical scans, cities, time periods, names

    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
     sinn
    0.50
    የት
    0.50
    בר
    0.49
    ة
    0.49
    товый
    0.48
    وسي
    0.47
    usic
    0.47
     fournit
    0.47
     {
    0.47
    ה
    0.47
    POSITIVE LOGITS
    observations
    0.59
    shoring
    0.59
    ?”
    0.52
    ra
    0.52
     Observations
    0.51
     আটক
    0.49
    Observations
    0.49
    iamiento
    0.49
    缜
    0.48
     Kidman
    0.48
    Activations Density 0.000%

    No Known Activations