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

    Neuronpedia

    Jacobian LensNEW
    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. 127142
    Prev
    Next
    INDEX
    Explanations

    hypothesis testing and affirmations

    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
     clipboard
    0.48
     history
    0.44
     efficiently
    0.44
     silently
    0.43
     instantly
    0.41
     stacked
    0.41
    *
    0.40
     recreating
    0.40
    ifed
    0.40
     practiced
    0.39
    POSITIVE LOGITS
    SizeType
    0.49
    のある
    0.49
     sehari
    0.49
    จึง
    0.49
     FLORIDA
    0.49
     जीवों
    0.48
     lượng
    0.47
     OHIO
    0.47
    テ
    0.47
     pekan
    0.46
    Activations Density 0.003%

    No Known Activations