© 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. 130127
    Prev
    Next
    INDEX
    Explanations

    advice

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

    asking you to stay

    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
     semblent
    0.55
     結果
    0.50
    `]
    0.48
     nettement
    0.47
     étrang
    0.47
    ecia
    0.46
     зокрема
    0.46
     それぞれ
    0.45
    🏟
    0.45
    罰
    0.45
    POSITIVE LOGITS
     VK
    0.49
     মোঃ
    0.49
     RMB
    0.47
     Você
    0.46
     sublime
    0.46
     CTRL
    0.46
     التحكم
    0.45
     Bits
    0.45
     Staub
    0.44
     keep
    0.44
    Activations Density 0.001%

    No Known Activations