© 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. 22-GEMMASCOPE-RES-131K
    7. 75398
    Prev
    Next
    INDEX
    Explanations

    HTML input types

    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_22/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
    presents
    -1.20
     nvm
    -1.13
     spazz
    -1.08
    뭄
    -1.07
    resizing
    -1.06
     Amethyst
    -1.05
     nazis
    -1.04
     electrica
    -1.04
     Srl
    -1.03
    욘
    -1.02
    POSITIVE LOGITS
     Why
    1.13
    ochond
    1.10
     What
    1.05
     queremos
    1.04
     quieres
    1.01
     koos
    0.99
     cand
    0.99
     WE
    0.97
    семь
    0.97
     polymer
    0.96
    Activations Density 0.002%

    No Known Activations