© 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. 93915
    Prev
    Next
    INDEX
    Explanations

    Proper names and titles

    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
    ROE
    -0.85
    čnost
    -0.82
     basically
    -0.81
     but
    -0.81
     motocic
    -0.79
     Various
    -0.79
     various
    -0.79
    čnosti
    -0.78
    読書
    -0.77
     drastically
    -0.77
    POSITIVE LOGITS
    verte
    1.05
     reflejo
    0.87
    ~\
    0.87
    }\
    0.82
    OUTPUT
    0.81
    蟾
    0.81
    人民币
    0.81
    lossing
    0.80
    +:+
    0.80
     EconPapers
    0.80
    Activations Density 0.009%

    No Known Activations