© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34639
    Prev
    Next
    INDEX
    Explanations

    code assembly types and rights

    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
    رائه
    -0.84
     accepté
    -0.81
    Geograf
    -0.79
     changing
    -0.77
    quarelle
    -0.76
     sizable
    -0.75
    Reprints
    -0.74
    labeling
    -0.74
     tùy
    -0.73
    ᱖
    -0.73
    POSITIVE LOGITS
    こし
    0.91
    works
    0.85
     гостиной
    0.82
    duce
    0.81
    ResumeLayout
    0.81
    æde
    0.81
     모든
    0.80
     CLS
    0.79
    getForm
    0.77
     câ
    0.77
    Activations Density 0.002%

    No Known Activations