© 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. 35519
    Prev
    Next
    INDEX
    Explanations

    change in quantity

    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
    떄
    -0.94
    metrist
    -0.94
    ‌.
    -0.90
    땐
    -0.90
    ?'
    -0.83
    射手
    -0.82
    Pontos
    -0.81
     or
    -0.81
     įva
    -0.80
    entras
    -0.79
    POSITIVE LOGITS
    始めて
    0.94
     such
    0.93
     nors
    0.92
    ^(@
    0.89
     about
    0.88
     Tienen
    0.88
     each
    0.85
    なんと
    0.85
    だけで
    0.84
     kezel
    0.84
    Activations Density 0.068%

    No Known Activations