© 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. 66925
    Prev
    Next
    INDEX
    Explanations

    reporting errors or diagnostic output

    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
    黢
    -1.05
    tvguidetime
    -1.02
    另一种
    -1.00
     keluarganya
    -0.99
    랏
    -0.93
     its
    -0.92
     andere
    -0.92
     kroner
    -0.89
    渐变
    -0.88
     senaste
    -0.86
    POSITIVE LOGITS
     “
    1.15
     ‘
    1.09
     energías
    1.02
     тази
    1.02
     referirse
    0.99
     '
    0.99
     there
    0.98
     pantallas
    0.98
    ❼
    0.96
    っていたので
    0.95
    Activations Density 0.005%

    No Known Activations