© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63244
    Prev
    Next
    INDEX
    Explanations

    use or utilize

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

    Ctrl+Alt+Del

    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
    Negative Logits
    st
    0.63
    discount
    0.59
    time
    0.58
    rs
    0.51
    s
    0.51
    ts
    0.50
    hr
    0.50
    rb
    0.50
    months
    0.49
    re
    0.49
    POSITIVE LOGITS
     உ
    0.57
     utiliser
    0.49
     permut
    0.47
     utilizar
    0.46
     utilizzare
    0.46
     utilice
    0.45
     calculating
    0.45
     használ
    0.45
     wykorzyst
    0.44
     utiliza
    0.43
    Activations Density 0.000%

    No Known Activations