© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54088
    Prev
    Next
    INDEX
    Explanations

    anyway

    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
     dokonce
    -0.91
    怎么能
    -0.87
     manchmal
    -0.85
    тири
    -0.82
     вдруг
    -0.82
     только
    -0.81
    omenta
    -0.80
    грамма
    -0.79
     مانند
    -0.79
     hubo
    -0.79
    POSITIVE LOGITS
     anyway
    3.20
    Anyway
    2.36
     anyways
    2.31
    anyway
    2.28
     sowieso
    1.98
     ohnehin
    1.95
     anyhow
    1.90
     zaten
    1.87
     already
    1.77
    反正
    1.76
    Activations Density 0.032%

    No Known Activations