© 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. 73031
    Prev
    Next
    INDEX
    Explanations

    code examples

    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
     papild
    -0.88
     viena
    -0.84
     한다
    -0.82
    érée
    -0.82
     veik
    -0.81
    rovna
    -0.80
    Paint
    -0.80
    ESM
    -0.79
     вести
    -0.78
    𝗾
    -0.77
    POSITIVE LOGITS
     accordance
    0.86
    므
    0.85
     method
    0.85
    体が
    0.78
     ず
    0.77
     tamaños
    0.77
     ordenado
    0.76
     textbooks
    0.76
    wo
    0.75
     –
    0.74
    Activations Density 0.057%

    No Known Activations