© 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. 26623
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and numbers

    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
    Another
    -1.12
    鍥
    -1.11
     cachorros
    -1.07
     ocultar
    -1.06
    heureusement
    -1.03
     innego
    -1.01
     resaltar
    -1.01
     soltar
    -1.01
     recordar
    -1.00
     apostar
    -0.99
    POSITIVE LOGITS
     nörd
    1.03
    と
    1.01
    res
    0.95
    ji
    0.94
    wa
    0.94
    8
    0.92
    6
    0.91
    dium
    0.91
     ی
    0.90
    ΙΑ
    0.90
    Activations Density 0.007%

    No Known Activations