© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    PHP class names and keywords

    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
     or
    -2.30
     to
    -2.02
    鱘
    -1.80
     Genuss
    -1.79
    酲
    -1.76
    祧
    -1.75
    alahkan
    -1.74
    ？！”
    -1.70
     Geschmack
    -1.69
     kebutuhan
    -1.67
    POSITIVE LOGITS
    ти
    2.09
    <td>
    2.08
    ...
    1.91
    她
    1.84
    ................
    1.80
    ............
    1.78
     όταν
    1.77
     persuading
    1.77
    ,:
    1.74
    ..(
    1.74
    Activations Density 0.009%

    No Known Activations