© 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. 10-GEMMASCOPE-RES-131K
    4. 90594
    Prev
    Next
    INDEX
    Explanations

    ordinarily, awfully

    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
    s
    -3.72
    </b>
    -2.91
    derdag
    -2.81
    (
    -2.36
    𓆜
    -2.28
    ꠥ
    -2.11
    ellido
    -2.09
    ють
    -2.08
    g
    -2.08
    ureusement
    -2.05
    POSITIVE LOGITS
    </h3>
    2.89
     knows
    2.52
    
    2.42
    providedIn
    2.38
     Hinblick
    2.20
    Tidak
    2.19
    ݮ
    2.17
     هو
    2.16
     不
    2.09
    媃
    2.06
    Activations Density 0.024%

    No Known Activations