© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11907
    Prev
    Next
    INDEX
    Explanations

    numbers and versions

    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
     one
    -1.05
     another
    -0.92
     for
    -0.84
     get
    -0.81
     after
    -0.80
     five
    -0.80
     getting
    -0.79
     веке
    -0.79
     professionals
    -0.79
     this
    -0.78
    POSITIVE LOGITS
     partecipare
    0.82
     Suggested
    0.81
     kurzem
    0.81
     كامل
    0.80
     kindled
    0.79
    仚
    0.79
     quoique
    0.79
     judging
    0.79
    鐃
    0.78
    CTION
    0.77
    Activations Density 0.011%

    No Known Activations