© 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. 26002
    Prev
    Next
    INDEX
    Explanations

    code and comments

    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
     that
    -0.97
     всегда
    -0.90
     תמיד
    -0.88
    entuk
    -0.88
     remained
    -0.87
     facilitating
    -0.86
    uarkan
    -0.86
     klachten
    -0.84
     همیشه
    -0.83
    𝔗
    -0.82
    POSITIVE LOGITS
     dám
    1.03
     decidedly
    1.01
     vastly
    0.98
     ridiculously
    0.95
    OO
    0.93
     diversos
    0.91
     diverses
    0.91
     immense
    0.91
    だら
    0.91
     dr
    0.90
    Activations Density 0.038%

    No Known Activations