© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57839
    Prev
    Next
    INDEX
    Explanations

    software license and distribution terms

    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
     опо
    -0.69
    凭
    -0.68
    OUT
    -0.65
     BigNumber
    -0.65
     mao
    -0.64
    etiqueta
    -0.63
     proget
    -0.63
     протя
    -0.62
    нская
    -0.62
     losing
    -0.62
    POSITIVE LOGITS
    compile
    0.75
    λικά
    0.69
    锺
    0.68
    essandro
    0.67
     Freddie
    0.66
    孙
    0.66
    ウッド
    0.65
    大使
    0.65
     blinked
    0.63
     caza
    0.63
    Activations Density 0.069%

    No Known Activations