© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 19379
    Prev
    Next
    INDEX
    Explanations

    copies and fine

    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
     miesią
    0.51
    ".*:
    0.49
     nights
    0.49
     naquela
    0.49
     nighttime
    0.49
     RetValue
    0.48
     acolo
    0.48
    ፑ
    0.47
     naquele
    0.47
     eighteen
    0.47
    POSITIVE LOGITS
    asa
    0.53
    are
    0.52
    ید
    0.48
    eli
    0.48
    if
    0.48
    istä
    0.47
    use
    0.47
    દ
    0.47
    ress
    0.47
    enses
    0.47
    Activations Density 0.000%

    No Known Activations