© 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. 22-GEMMASCOPE-RES-131K
    4. 104260
    Prev
    Next
    INDEX
    Explanations

    lessons from experience

    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
     for
    -1.36
     after
    -1.11
     in
    -1.08
     для
    -1.01
    Beschrijving
    -0.97
     there
    -0.96
     друзьями
    -0.91
     if
    -0.89
     busca
    -0.89
    як
    -0.88
    POSITIVE LOGITS
     experience
    1.72
     experiences
    1.60
     experiências
    1.40
     erfaring
    1.21
    experience
    1.20
     expériences
    1.19
    orle
    1.15
     ervaring
    1.12
     esperienza
    1.10
     erfaren
    1.10
    Activations Density 0.062%

    No Known Activations