© 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. 10-GEMMASCOPE-RES-131K
    7. 128738
    Prev
    Next
    INDEX
    Explanations

    android code snippets `R.id`

    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_10/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
    0
    -1.91
    x
    -1.66
    B
    -1.58
    g
    -1.53
    et
    -1.52
    3
    -1.52
    y
    -1.52
    m
    -1.51
    也是
    -1.50
    ars
    -1.48
    POSITIVE LOGITS
     semejante
    1.67
    xvii
    1.61
     such
    1.61
    鈮
    1.59
     dicha
    1.58
     ligeramente
    1.56
    🦽
    1.52
    ionato
    1.51
     that
    1.48
    ionage
    1.48
    Activations Density 0.001%

    No Known Activations