© 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. 31-GEMMASCOPE-2-RES-262K
    7. 144463
    Prev
    Next
    INDEX
    Explanations

    government investment

    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_31_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
     compress
    0.49
    तीय
    0.48
     हों
    0.46
     dapat
    0.45
     Ví
    0.45
     fazem
    0.45
     ス
    0.45
     daje
    0.45
    щает
    0.44
     lui
    0.44
    POSITIVE LOGITS
    kast
    0.45
    coated
    0.43
    logged
    0.43
    infused
    0.42
     υπηρε
    0.42
    categorical
    0.41
    trz
    0.41
    victim
    0.40
    胆
    0.40
    kad
    0.40
    Activations Density 0.001%

    No Known Activations