© 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. 73265
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
     it
    -0.96
    romechanical
    -0.86
     bicara
    -0.86
     gebruik
    -0.84
     any
    -0.84
    Kaynak
    -0.83
     their
    -0.83
     so
    -0.82
     nasz
    -0.82
    アレ
    -0.81
    POSITIVE LOGITS
     entweder
    1.03
     OMB
    0.98
     ebenfalls
    0.92
     figliu
    0.92
     [''
    0.91
    either
    0.90
     enten
    0.89
     있으며
    0.88
    ės
    0.87
     ovate
    0.86
    Activations Density 0.008%

    No Known Activations