© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98628
    Prev
    Next
    INDEX
    Explanations

    currently in a state

    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
     both
    -1.29
    aussi
    -1.21
     både
    -1.20
    BOTH
    -1.19
    both
    -1.17
     famed
    -1.12
     kutoka
    -1.12
     durante
    -1.10
     problemet
    -1.08
     BOTH
    -1.07
    POSITIVE LOGITS
     currently
    1.70
     in
    1.52
     still
    1.46
    Currently
    1.36
    rester
    1.22
     obecnie
    1.22
     сейчас
    1.21
     awaiting
    1.19
    currently
    1.19
     Currently
    1.18
    Activations Density 0.032%

    No Known Activations