© 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. 16-GEMMASCOPE-2-RES-262K
    7. 35564
    Prev
    Next
    INDEX
    Explanations

    pen followed by specific words

    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_16_width_262k_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
    t
    1.84
    т
    1.55
    ت
    1.51
    in
    1.47
    u
    1.39
    る
    1.39
    ز
    1.38
    то
    1.38
    ле
    1.34
    li
    1.33
    POSITIVE LOGITS
     pen
    1.14
    Pen
    1.02
    PEN
    0.97
    IFT
    0.92
     quell
    0.92
    AK
    0.90
     immobil
    0.90
     beho
    0.87
     estern
    0.86
    Hat
    0.85
    Activations Density 0.005%

    No Known Activations