© 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. 34-GEMMASCOPE-RES-131K
    7. 69820
    Prev
    Next
    INDEX
    Explanations

    remained unchanged, short lived

    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
     folks
    -1.42
     gotten
    -1.30
     behaviors
    -1.26
     еще
    -1.26
     awfully
    -1.18
     unfavorable
    -1.16
     sorta
    -1.13
     путем
    -1.11
     geologic
    -1.11
     laborers
    -1.10
    POSITIVE LOGITS
    Whilst
    1.20
     Whilst
    1.16
     whilst
    1.14
    🏟
    1.02
     spelt
    0.98
     олив
    0.97
     TÉCN
    0.92
     specialist
    0.91
     learnt
    0.91
     avocat
    0.90
    Activations Density 0.106%

    No Known Activations