© 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. 34-GEMMASCOPE-RES-131K
    7. 12007
    Prev
    Next
    INDEX
    Explanations

    edit or greetings

    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_34/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
    tites
    -0.93
    𝘢
    -0.82
    ifter
    -0.80
    CreateModel
    -0.78
    tilor
    -0.77
     нового
    -0.76
    forme
    -0.76
    ولي
    -0.75
    ****/
    -0.73
    年
    -0.73
    POSITIVE LOGITS
    EDIT
    1.20
    Edit
    1.12
     EDIT
    1.10
     edit
    0.98
     Edit
    0.96
    edit
    0.94
     Grüße
    0.91
    OTO
    0.87
     Steve
    0.87
     $-
    0.86
    Activations Density 0.023%

    No Known Activations