© 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. 83162
    Prev
    Next
    INDEX
    Explanations

    characterizes

    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
    ônia
    -1.00
     morphism
    -0.87
    awakeFromNib
    -0.86
    ⠳
    -0.86
     conjun
    -0.86
    conven
    -0.85
    Materiale
    -0.84
    verton
    -0.82
    ℰ
    -0.81
    菅
    -0.79
    POSITIVE LOGITS
     characterize
    3.66
     characterizes
    3.50
     characterized
    2.91
     caracter
    2.78
     characterizing
    2.70
     characterised
    2.66
    character
    2.64
     caratter
    2.55
     character
    2.52
     caracteriza
    2.47
    Activations Density 0.113%

    No Known Activations