© 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. 75234
    Prev
    Next
    INDEX
    Explanations

    impaired biological functions

    np_acts-logits-general · gemini-2.5-flash-lite

    dysfunction or impairment in cellular and biological processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     verhind
    -1.25
     gouttes
    -1.19
     faciliter
    -1.16
     conserver
    -1.13
     utilisent
    -1.02
    ᠌
    -1.02
    よりは
    -1.01
     PriorityQueue
    -1.01
     exemplaire
    -1.01
     doivent
    -0.99
    POSITIVE LOGITS
     essential
    1.57
     adequate
    1.52
     vital
    1.50
     ability
    1.46
     well
    1.44
     due
    1.42
     even
    1.38
     important
    1.33
    Because
    1.30
     Because
    1.30
    Activations Density 0.178%

    No Known Activations