© 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-16K
    7. 12350
    Prev
    Next
    INDEX
    Explanations

    pen followed by hal, ural, or ise

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intensifying
    0.46
     intensify
    0.45
     intensification
    0.44
     kē
    0.41
    かん
    0.40
     uttering
    0.39
    قق
    0.39
     ][
    0.39
    瓒
    0.39
     forcing
    0.38
    POSITIVE LOGITS
    Pen
    0.82
     pen
    0.78
     пен
    0.76
     pén
    0.75
     penet
    0.71
     PEN
    0.69
     Pen
    0.68
    PEN
    0.68
     penetration
    0.66
    pen
    0.66
    Activations Density 0.057%

    No Known Activations