© 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. 71789
    Prev
    Next
    INDEX
    Explanations

    list elements

    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
     redondo
    -1.07
    鐧
    -1.03
     héroe
    -1.02
     citado
    -0.98
     sudah
    -0.96
     voulons
    -0.96
     때문
    -0.96
    ittäin
    -0.95
     gabinete
    -0.92
    imbang
    -0.92
    POSITIVE LOGITS
    en
    1.00
    set
    1.00
     other
    0.87
     sprawia
    0.86
    um
    0.86
    ӧ
    0.85
    nou
    0.84
    uk
    0.83
    ington
    0.82
    tau
    0.82
    Activations Density 0.000%

    No Known Activations