© 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. 20571
    Prev
    Next
    INDEX
    Explanations

    biography

    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
    ?"
    -2.91
    enablog
    -2.45
    樒
    -2.41
     replete
    -2.31
    !"
    -2.27
    磲
    -2.19
    ЛИ
    -2.16
    埽
    -2.16
     asesin
    -2.13
    樯
    -2.13
    POSITIVE LOGITS
    ↵
    3.45
    .
    3.20
     Hinsicht
    2.56
    ’，
    2.42
    ጵ
    2.39
     yapan
    2.39
    ”،
    2.25
    焄
    2.22
     ettiği
    2.20
     маленьких
    2.13
    Activations Density 0.004%

    No Known Activations