© 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-16K
    7. 1323
    Prev
    Next
    INDEX
    Explanations

    easier, harder, more

    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_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
    '
    0.47
     exists
    0.46
    ແມ່ນ
    0.46
     estamos
    0.46
    ή
    0.45
    已
    0.45
     estão
    0.45
     están
    0.44
    被
    0.44
     arose
    0.44
    POSITIVE LOGITS
     훨씬
    0.66
     more
    0.59
     የበለጠ
    0.58
     easier
    0.57
    更加
    0.56
     znacznie
    0.55
     immensely
    0.55
     considerably
    0.54
     tremendously
    0.53
     enormously
    0.50
    Activations Density 0.228%

    No Known Activations