© 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. 35398
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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
     for
    -1.18
    themselves
    -1.16
     themselves
    -1.04
     wobei
    -1.01
     with
    -1.01
     only
    -0.93
     Their
    -0.91
    НЫЙ
    -0.90
     because
    -0.90
     such
    -0.88
    POSITIVE LOGITS
    țin
    1.11
    ține
    1.03
    tamia
    1.02
    ֊
    0.94
     ہم
    0.94
    鐨
    0.93
    现在
    0.92
     which
    0.91
    および
    0.90
    ților
    0.90
    Activations Density 0.065%

    No Known Activations