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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35702
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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
    を
    -1.14
    Mengapa
    -1.11
     only
    -1.10
     but
    -1.06
    これは
    -1.05
    ～～
    -1.05
    が
    -0.96
    だが
    -0.96
    儀式
    -0.95
    指標
    -0.94
    POSITIVE LOGITS
     mischie
    1.16
    場合には
    1.15
    為に
    1.11
    
    1.08
    ところに
    1.07
     jenen
    1.05
    の時に
    1.04
     unspeak
    1.02
    あー
    1.02
     thoſe
    1.02
    Activations Density 0.013%

    No Known Activations