© 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. 129431
    Prev
    Next
    INDEX
    Explanations

    k 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
    jScrollPane
    -0.91
     フレーム
    -0.88
     marts
    -0.86
    ಎ
    -0.84
    喜歡
    -0.84
     Samen
    -0.83
     staffel
    -0.83
     facendo
    -0.83
    stående
    -0.83
    Unspecified
    -0.83
    POSITIVE LOGITS
     this
    1.20
     before
    1.16
     previous
    1.03
     brisk
    1.00
     its
    0.99
     since
    0.94
     Before
    0.88
    ácti
    0.87
     (!
    0.87
    ometries
    0.87
    Activations Density 0.001%

    No Known Activations