© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38286
    Prev
    Next
    INDEX
    Explanations

    protobuf, ActiveRecord, presets

    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
     chaque
    -1.48
     all
    -1.48
     each
    -1.48
     by
    -1.42
     for
    -1.39
    ;
    -1.36
     its
    -1.24
     to
    -1.24
    phans
    -1.23
    ⌗
    -1.23
    POSITIVE LOGITS
     Hinsicht
    1.55
    姈
    1.45
     ścian
    1.38
    épisode
    1.38
    躥
    1.34
    
    1.30
    隂
    1.30
     ovviamente
    1.30
     ozdob
    1.30
    sandalia
    1.30
    Activations Density 0.001%

    No Known Activations