© 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. 221214
    Prev
    Next
    INDEX
    Explanations

    matching colors

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

    offering romantic and emotional themes

    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
     ambient
    0.60
     contains
    0.52
     ax
    0.50
     サ
    0.48
     config
    0.48
     Ambient
    0.47
     activation
    0.47
     Used
    0.46
     adaptive
    0.45
     optimized
    0.45
    POSITIVE LOGITS
     финансо
    0.52
    꿋
    0.50
     юриди
    0.50
     vehemently
    0.50
    жден
    0.49
     vehement
    0.49
     чувство
    0.48
     демокра
    0.47
     досто
    0.47
     countrymen
    0.47
    Activations Density 0.000%

    No Known Activations