© 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. 72982
    Prev
    Next
    INDEX
    Explanations

    maximum sequence

    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
     toekomst
    -0.94
    ריה
    -0.91
     avond
    -0.90
     mujeres
    -0.90
     kvinnor
    -0.89
     quinto
    -0.88
    ってみて
    -0.88
    푉
    -0.88
     espé
    -0.87
     collè
    -0.86
    POSITIVE LOGITS
     last
    1.16
     max
    1.16
    max
    1.05
     maximum
    0.98
    maxsize
    0.94
     Max
    0.94
    LAST
    0.93
     xxii
    0.93
     maximal
    0.92
    car
    0.91
    Activations Density 0.008%

    No Known Activations