© 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. 69080
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     vodu
    -0.96
    consejos
    -0.96
    向けの
    -0.96
     srdce
    -0.94
    はな
    -0.94
     rze
    -0.94
    んですよ
    -0.94
     stanov
    -0.93
    pośred
    -0.93
    awakeFromNib
    -0.93
    POSITIVE LOGITS
     itself
    1.14
     other
    1.03
     Himself
    0.98
    itself
    0.96
     warung
    0.93
     Itself
    0.91
     uur
    0.90
    という感じ
    0.90
     possam
    0.89
    自己的
    0.89
    Activations Density 0.030%

    No Known Activations