© 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. 39544
    Prev
    Next
    INDEX
    Explanations

    home features and attributes

    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
     UILabel
    -1.69
     IBOutlet
    -1.62
     UIAlert
    -1.57
     forKey
    -1.55
     UITableViewCell
    -1.52
     JpaRepository
    -1.48
     glyphicon
    -1.48
     CITED
    -1.45
     NSCoder
    -1.45
    ocrats
    -1.43
    POSITIVE LOGITS
     a
    2.47
     plenty
    1.91
     an
    1.65
     and
    1.55
     lots
    1.48
     strong
    1.34
    salomon
    1.31
     함께
    1.30
     huge
    1.27
     multiple
    1.26
    Activations Density 0.028%

    No Known Activations