© 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. 10-GEMMASCOPE-RES-131K
    7. 131021
    Prev
    Next
    INDEX
    Explanations

    vanity, vain, pretentious

    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_10/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
    呿
    -3.36
     But
    -2.88
     Which
    -2.86
    摃
    -2.80
     was
    -2.64
    筴
    -2.41
    搥
    -2.41
     are
    -2.39
     sottile
    -2.39
     Then
    -2.38
    POSITIVE LOGITS
    }
    2.95
     Vanity
    2.19
     glitter
    2.16
    a
    2.13
     blurred
    2.08
    𖡼
    2.06
     مباراة
    2.05
     calories
    2.03
    ”
    1.98
    Rptr
    1.97
    Activations Density 0.002%

    No Known Activations