© 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. 33122
    Prev
    Next
    INDEX
    Explanations

    numbers followed by f

    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
     unique
    -1.02
     moletom
    -0.93
     rusak
    -0.91
     getting
    -0.91
     similar
    -0.90
     microfibra
    -0.89
     Stadion
    -0.88
     solely
    -0.88
     legger
    -0.86
    epresidente
    -0.85
    POSITIVE LOGITS
    eventually
    1.16
    innan
    0.98
    tranh
    0.98
     uiteindelijk
    0.97
    Eventually
    0.94
     Unterscheidung
    0.94
    visning
    0.93
     eventually
    0.93
     locura
    0.93
     enshr
    0.91
    Activations Density 0.010%

    No Known Activations