© 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. 69130
    Prev
    Next
    INDEX
    Explanations

    parameters `{indent=on&start=0...`code `Converter={StaticResource...`diagram `...every node/.style={rectangle, rounded corners, draw...`code `...access_token={AIzaSyB740elm...`code `...asset={ASSET UPLOAD...`diagram `\begin{tikzpicture}[>=stealth, every node/.style={rectangle, rounded corners, draw, minimum size=0.75cm}] \graph [tree layout, grow`diagram `for tree={circle,draw, l sep=20pt}`

    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
     or
    -2.84
    หรือ
    -2.55
    ﮕ
    -2.33
    筏
    -2.27
    ～！
    -2.20
    蚤
    -2.19
    妊
    -2.14
    ilares
    -2.09
    udadera
    -2.09
    ～。
    -2.09
    POSITIVE LOGITS
    4
    3.19
    0
    2.95
    -“
    2.84
    6
    2.64
    </em>
    2.63
    7
    2.61
    9
    2.59
    際の
    2.56
    5
    2.56
    1
    2.53
    Activations Density 0.002%

    No Known Activations