© 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. 53980
    Prev
    Next
    INDEX
    Explanations

    theme or motto

    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
    handeling
    -1.06
    بالإنجليزية
    -0.98
    projekt
    -0.96
     progetto
    -0.91
    Projek
    -0.87
    Odour
    -0.85
     علاقه
    -0.85
    Enciclopedia
    -0.85
     República
    -0.85
    Hü
    -0.85
    POSITIVE LOGITS
     letz
    0.97
    Building
    0.95
    €“
    0.92
     thème
    0.91
     together
    0.91
    towards
    0.91
     TOGETHER
    0.90
    vancing
    0.90
    ghter
    0.87
     towards
    0.86
    Activations Density 0.020%

    No Known Activations