© 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. 73198
    Prev
    Next
    INDEX
    Explanations

    this and target in code

    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
     dava
    -1.01
     since
    -0.95
    后来
    -0.88
    twin
    -0.86
     after
    -0.86
     broj
    -0.85
     Tecn
    -0.84
     munici
    -0.83
     twin
    -0.82
    laken
    -0.81
    POSITIVE LOGITS
    ステム
    1.05
     sommige
    0.97
    ventud
    0.96
     clicked
    0.95
     creado
    0.93
     acento
    0.93
     proporción
    0.90
     distanced
    0.90
     bepaalde
    0.90
     belonged
    0.89
    Activations Density 0.010%

    No Known Activations