© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72718
    Prev
    Next
    INDEX
    Explanations

    language and code constructs

    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
    皤
    -1.05
    usually
    -1.02
    ctivo
    -1.00
    hability
    -1.00
    inste
    -0.98
     heilig
    -0.98
     gefe
    -0.98
    ℟
    -0.96
     identifiable
    -0.95
     略
    -0.94
    POSITIVE LOGITS
    точник
    1.11
     กรัม
    1.01
    Transk
    0.98
    씻
    0.96
     Descri
    0.96
     varias
    0.96
    Ingrédients
    0.96
    ựu
    0.94
     anvä
    0.94
     tijdens
    0.94
    Activations Density 0.000%

    No Known Activations