© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101721
    Prev
    Next
    INDEX
    Explanations

    Williams had

    np_acts-logits-general · gemini-2.5-flash-lite

    reliable transcript instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    רו
    0.49
    പ്പോള്‍
    0.41
     மூல
    0.39
    although
    0.39
     동안
    0.38
     متعدد
    0.37
    悰
    0.37
    긍
    0.37
     సమయంలో
    0.37
     رحمه
    0.37
    POSITIVE LOGITS
     are
    0.47
    peed
    0.47
    数を
    0.43
     шанс
    0.43
    catalog
    0.42
     rispar
    0.42
     forested
    0.42
    speed
    0.42
     indicate
    0.41
     indicator
    0.41
    Activations Density 0.000%

    No Known Activations