© 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. 22-GEMMASCOPE-RES-131K
    7. 84462
    Prev
    Next
    INDEX
    Explanations

    committed to positive principles

    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_22/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
     after
    -1.56
     for
    -1.38
     or
    -1.37
     perhaps
    -1.28
     they
    -1.26
     without
    -1.24
     four
    -1.21
     presumably
    -1.21
    ardı
    -1.20
     time
    -1.19
    POSITIVE LOGITS
     our
    1.69
     هر
    1.56
     inaugu
    1.30
     ourselves
    1.27
    every
    1.23
    whenever
    1.21
     setiap
    1.21
    และ
    1.20
     its
    1.19
    Wherever
    1.18
    Activations Density 0.039%

    No Known Activations