© 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. 60919
    Prev
    Next
    INDEX
    Explanations

    scheduling

    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
     we
    -2.94
    埽
    -2.83
    𖣘
    -2.83
    }$
    -2.58
     Officially
    -2.50
    AddTagHelper
    -2.44
    ╽
    -2.44
    VERTISEMENT
    -2.31
    vacy
    -2.27
     nommé
    -2.27
    POSITIVE LOGITS
    ဴ
    3.11
    '
    2.56
    辚
    2.55
    ஂ
    2.44
    l
    2.44
     sju
    2.42
     lindos
    2.33
     =
    2.27
     ucc
    2.22
    しましたが
    2.22
    Activations Density 0.007%

    No Known Activations