© 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. 102976
    Prev
    Next
    INDEX
    Explanations

    UK universities and research institutes

    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
     counseling
    -0.96
     Counseling
    -0.90
     остается
    -0.89
     analyzed
    -0.86
    効率
    -0.85
     neighborhood
    -0.85
     favorable
    -0.83
     grayish
    -0.82
     soluzione
    -0.82
     harbors
    -0.82
    POSITIVE LOGITS
     UK
    1.63
    UK
    1.34
    LSTM
    1.27
    英国
    1.26
    Imperial
    1.18
     британ
    1.16
     UCL
    1.13
    UCL
    1.13
    Britain
    1.10
     Imperial
    1.06
    Activations Density 0.092%

    No Known Activations