© 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. 84966
    Prev
    Next
    INDEX
    Explanations

    asking for clarification

    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
     would
    -1.34
     θα
    -1.20
    Imagine
    -1.10
    imagine
    -1.08
     avrebbe
    -1.07
    would
    -1.03
    如何
    -0.99
     素人
    -0.98
    ētu
    -0.94
    ーめん
    -0.93
    POSITIVE LOGITS
     is
    2.70
     are
    2.47
    难道
    1.88
     Is
    1.85
     did
    1.80
     Are
    1.80
     was
    1.77
     Did
    1.71
    Is
    1.50
     were
    1.49
    Activations Density 0.051%

    No Known Activations