© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21196
    Prev
    Next
    INDEX
    Explanations

    various things

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

    special characters and non-English words

    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
     H
    0.55
     leveraging
    0.55
    0.53
     over
    0.52
     L
    0.51
     Leveraging
    0.50
     BFF
    0.49
     Re
    0.49
     previously
    0.48
     transitioned
    0.48
    POSITIVE LOGITS
    いろいろ
    0.63
     allerlei
    0.61
    ೪
    0.60
    各类
    0.56
    学ぶ
    0.56
    เรื่อง
    0.55
    ོད་
    0.55
    こともある
    0.55
    कौन
    0.54
     लोकांना
    0.54
    Activations Density 0.005%

    No Known Activations