© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20072
    Prev
    Next
    INDEX
    Explanations

    Gabriel or Abraham names

    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
    2
    -3.33
    5
    -3.25
    ll
    -3.23
    )
    -3.19
    8
    -3.14
    '
    -2.98
    3
    -2.98
     unveils
    -2.89
    越是
    -2.78
    7
    -2.78
    POSITIVE LOGITS
    𞤢
    3.09
    桄
    3.02
    觏
    2.94
    沺
    2.89
    ↑↑↑</
    2.81
    轫
    2.81
    骓
    2.80
    罍
    2.80
    𖥧
    2.80
    酲
    2.77
    Activations Density 0.006%

    No Known Activations