© 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. 79557
    Prev
    Next
    INDEX
    Explanations

    usual / customary / typical

    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
     It
    -0.94
     Until
    -0.92
     larg
    -0.91
    ֖
    -0.88
    ider
    -0.86
     also
    -0.85
     You
    -0.84
    ⼤
    -0.84
     We
    -0.83
     вто
    -0.83
    POSITIVE LOGITS
     usual
    1.72
    いつも
    1.45
    いつもの
    1.45
    usual
    1.38
     trademark
    1.30
     customary
    1.28
    相変わらず
    1.27
     again
    1.23
     очеред
    1.23
     всегда
    1.20
    Activations Density 0.060%

    No Known Activations