© 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. 34-GEMMASCOPE-RES-131K
    7. 82824
    Prev
    Next
    INDEX
    Explanations

    concluding or ending

    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_34/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
    Caracteristici
    -0.92
     Cách
    -0.85
    前言
    -0.82
    стта
    -0.79
     FontWeight
    -0.79
     chuẩn
    -0.78
    StateMachine
    -0.77
    Frente
    -0.77
     azar
    -0.77
     Clash
    -0.76
    POSITIVE LOGITS
     ending
    1.48
     end
    1.34
     concluding
    1.26
    结束
    1.23
     concludes
    1.23
     finishing
    1.22
     ends
    1.19
     endings
    1.17
     closing
    1.16
     outro
    1.15
    Activations Density 0.000%

    No Known Activations