© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4945
    Prev
    Next
    INDEX
    Explanations

    words indicating state or relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    。
    0.97
    ³.
    0.91
    $.
    0.91
    _.
    0.90
    ().
    0.88
    \,.
    0.86
    ।
    0.86
    ～。
    0.84
     _.
    0.82
    <unused2221>
    0.81
    POSITIVE LOGITS
     Unfortunately
    1.01
     Additionally
    0.88
     Meanwhile
    0.82
     Also
    0.82
    Unfortunately
    0.81
     During
    0.81
     This
    0.80
     Which
    0.79
     Ayrıca
    0.78
     Eventually
    0.77
    Activations Density 0.356%

    No Known Activations