© 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. 95660
    Prev
    Next
    INDEX
    Explanations

    success leads to action

    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
    やっと
    -1.16
     Америка
    -1.01
    ようやく
    -0.98
    或者
    -0.92
    久しぶりの
    -0.91
     ersten
    -0.88
     Majors
    -0.86
    Datuak
    -0.85
     Kenobi
    -0.85
    久しぶりに
    -0.85
    POSITIVE LOGITS
     then
    1.45
     further
    1.33
     other
    1.33
     continued
    1.33
     subsequent
    1.24
     continue
    1.23
     recommend
    1.20
     encouraged
    1.13
     recommended
    1.13
     expand
    1.11
    Activations Density 0.041%

    No Known Activations