© 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. 77870
    Prev
    Next
    INDEX
    Explanations

    photo art

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

    legal, marry, epoch

    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
    Not in Any Lists

    No Comments

    Negative Logits
     друзья
    0.45
     בין
    0.45
    ঢাকা
    0.44
     ölç
    0.43
     сопровожда
    0.41
    atürk
    0.41
     begleitet
    0.41
    蓼
    0.41
    ちなみに
    0.41
     kamb
    0.41
    POSITIVE LOGITS
     stepped
    0.46
     inaccurate
    0.46
     alluded
    0.46
     brink
    0.44
     Sweep
    0.43
     reposition
    0.43
    NewUrl
    0.42
     посту
    0.42
     manufacturing
    0.41
     Stable
    0.41
    Activations Density 0.000%

    No Known Activations