© 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. 10-GEMMASCOPE-RES-131K
    7. 39185
    Prev
    Next
    INDEX
    Explanations

    parentheses in code/syntax

    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_10/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
    </b>
    -3.69
    I
    -3.25
    ”
    -3.22
    _
    -3.00
    L
    -2.83
    “
    -2.80
    0
    -2.69
    ”.
    -2.50
    -2.48
    _{
    -2.47
    POSITIVE LOGITS
     There
    2.69
    אלי
    2.34
    ⮚
    2.34
     ͡°
    2.28
    𝗛
    2.23
    𝗗
    2.20
    老爷子
    2.19
    癩
    2.17
     yanı
    2.17
     restrained
    2.14
    Activations Density 0.035%
    No Known Activations