© 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. 193216
    Prev
    Next
    INDEX
    Explanations

    refused to

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

    portfolio integration PowerPoint investor

    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
    ර
    0.47
    错误的
    0.46
     inaccuracies
    0.44
    -​
    0.43
    residential
    0.42
     residential
    0.41
     scalars
    0.41
    线下
    0.41
    ativistic
    0.40
     diameters
    0.40
    POSITIVE LOGITS
     it
    0.59
     ℃
    0.52
     controllo
    0.51
     agréable
    0.48
    o
    0.48
    🆒
    0.48
     couleur
    0.46
    p
    0.46
     giữ
    0.44
     contrôle
    0.44
    Activations Density 0.000%

    No Known Activations