© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 56326
    Prev
    Next
    INDEX
    Explanations

    modal dialogs and popups

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Prompt
    0.60
    Prompt
    0.59
     prompt
    0.57
     prompting
    0.57
     prompts
    0.54
    欵
    0.50
     ask
    0.47
     prompted
    0.47
    問
    0.45
     srebr
    0.44
    POSITIVE LOGITS
    backdrop
    0.61
    modal
    0.54
    fade
    0.49
     مود
    0.49
    MovieModal
    0.49
     backdrop
    0.47
    iziModal
    0.46
    AddModel
    0.44
     Backdrop
    0.44
     blackout
    0.42
    Activations Density 0.014%

    No Known Activations