© 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. 11184
    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
    т
    -2.33
    replyreport
    -2.33
    dersfield
    -2.11
    の商品
    -2.06
     asomb
    -1.99
    㩒
    -1.98
    を開始
    -1.95
    を書く
    -1.89
    AuthContext
    -1.88
    不论
    -1.84
    POSITIVE LOGITS
    e
    2.44
    もある
    2.05
    z
    1.93
    m
    1.91
    ol
    1.88
    c
    1.84
    鼍
    1.80
     потому
    1.75
    lo
    1.74
    缡
    1.74
    Activations Density 0.093%

    No Known Activations