© 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. 128488
    Prev
    Next
    INDEX
    Explanations

    structured data and code

    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
    Ď
    -1.16
     kolejne
    -1.02
    yourself
    -0.96
    времен
    -0.94
     pierwsze
    -0.93
    Ÿ
    -0.93
     nueces
    -0.90
     pierwszy
    -0.90
     BEEN
    -0.90
     dager
    -0.88
    POSITIVE LOGITS
     different
    0.93
    などを
    0.92
     peculiarity
    0.91
     FDP
    0.91
    dateTimePicker
    0.91
    ⮚
    0.89
    Diplom
    0.88
    Beschrijving
    0.87
    Inves
    0.87
     (~(
    0.86
    Activations Density 0.008%

    No Known Activations