© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72265
    Prev
    Next
    INDEX
    Explanations

    coding variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    などは
    -1.09
     with
    -1.02
     already
    -1.02
    ไม่มี
    -0.98
    などを
    -0.96
    などが
    -0.94
     wants
    -0.93
    頸
    -0.91
    และ
    -0.91
     is
    -0.90
    POSITIVE LOGITS
    際に
    1.24
    際の
    1.15
     ciem
    1.05
    ்ச
    1.05
     imidlertid
    1.04
    んでしょう
    1.03
    明日は
    1.02
    際には
    1.02
    んだろう
    1.02
    あー
    1.02
    Activations Density 0.008%

    No Known Activations