© 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. 75658
    Prev
    Next
    INDEX
    Explanations

    heart will remain

    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
     betek
    -1.53
     ferien
    -1.50
     bedien
    -1.48
    雠
    -1.46
     复古
    -1.46
     magasiner
    -1.45
    ◝
    -1.44
    ﻊ
    -1.44
    idjan
    -1.43
     decorados
    -1.43
    POSITIVE LOGITS
    in
    1.66
     only
    1.50
     [
    1.42
    ’
    1.39
    f
    1.39
    J
    1.37
    p
    1.33
    ou
    1.27
    l
    1.27
     remain
    1.26
    Activations Density 0.012%

    No Known Activations