© 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. 84300
    Prev
    Next
    INDEX
    Explanations

    will be followed by outcome

    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
     now
    -1.27
     think
    -1.26
     it
    -1.24
     many
    -1.21
     find
    -1.10
    苫
    -1.08
    uiente
    -1.06
    WindowEvent
    -1.05
     seems
    -1.05
     just
    -1.03
    POSITIVE LOGITS
     persoonlijke
    1.25
     erwor
    1.20
    こんな感じで
    1.19
    ありが
    1.17
    デメリット
    1.16
    僕が
    1.12
    鱚
    1.11
     toekomst
    1.10
     unmittel
    1.08
    どのような
    1.08
    Activations Density 0.022%

    No Known Activations