© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22476
    Prev
    Next
    INDEX
    Explanations

    abstract states and conditions

    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
    -3.38
    e
    -3.17
    or
    -3.03
    是
    -2.98
    她
    -2.88
    价格
    -2.84
    er
    -2.81
     There
    -2.81
    方法
    -2.78
    眼睛
    -2.73
    POSITIVE LOGITS
    趼
    4.56
    汭
    4.06
    弍
    3.48
    
    3.36
    𐄁
    3.25
    灕
    3.25
    ikusbot
    3.11
    饹
    3.08
    鄠
    3.08
    箩
    3.02
    Activations Density 0.021%

    No Known Activations