© 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. 33303
    Prev
    Next
    INDEX
    Explanations

    limited quantity or size

    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
     by
    -0.90
    ്ല
    -0.87
     just
    -0.79
    єдна
    -0.79
    izações
    -0.77
    zman
    -0.75
     již
    -0.74
     немного
    -0.74
     أيضًا
    -0.73
    тости
    -0.73
    POSITIVE LOGITS
     entire
    1.44
     whole
    1.16
     milliers
    1.10
    Huge
    1.10
     thousands
    1.09
    huge
    1.04
    Entire
    1.01
     całą
    1.01
     cały
    1.01
    Whole
    0.99
    Activations Density 0.045%

    No Known Activations