© 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-16K
    7. 1642
    Prev
    Next
    INDEX
    Explanations

    demonstrates qualities or actions

    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
    z
    0.46
     パ
    0.44
     श्रृंखला
    0.43
    すべての
    0.43
     TO
    0.43
     waterfall
    0.42
     spectra
    0.41
    <blockquote>
    0.41
     memutuskan
    0.40
    POSITIVE LOGITS
     dimost
    0.66
     commitment
    0.63
     eagerness
    0.62
     demuestra
    0.62
     willingness
    0.61
     демонстри
    0.59
    意志
    0.59
     impatience
    0.57
     demonstrates
    0.57
     demonstrate
    0.55
    Activations Density 0.388%

    No Known Activations