© 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. 1023
    Prev
    Next
    INDEX
    Explanations

    small amounts or quantities

    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
     further
    -1.41
     ním
    -1.39
    心中
    -1.29
     example
    -1.27
     altre
    -1.25
     problem
    -1.24
    atieve
    -1.24
     infância
    -1.24
     tratados
    -1.24
     other
    -1.23
    POSITIVE LOGITS
     Crucial
    1.46
    ING
    1.29
    hver
    1.24
    🫓
    1.20
     by
    1.20
    certain
    1.19
     CascadeType
    1.16
     endeav
    1.16
    が上が
    1.16
     imbal
    1.16
    Activations Density 0.152%

    No Known Activations