© 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. 4263
    Prev
    Next
    INDEX
    Explanations

    Val place names and words

    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
     andato
    -0.77
     vorrei
    -0.75
    Kedua
    -0.74
    simpan
    -0.73
     ティー
    -0.72
     vincit
    -0.71
    レンタイン
    -0.71
    hubung
    -0.70
     объ
    -0.69
    ležit
    -0.69
    POSITIVE LOGITS
     val
    1.23
     Val
    1.15
    Val
    0.96
     VAL
    0.91
     वाल
    0.90
     Valk
    0.89
     Valer
    0.89
     Validator
    0.87
    mentable
    0.85
    ρούν
    0.85
    Activations Density 0.016%

    No Known Activations