© 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. 75757
    Prev
    Next
    INDEX
    Explanations

    sufficient documentation or requirements

    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
     sedangkan
    -1.22
     very
    -1.11
     more
    -1.09
     більш
    -1.09
     almost
    -1.07
     dozens
    -1.07
     hundreds
    -1.05
     enormous
    -1.01
     alot
    -0.98
     jendela
    -0.98
    POSITIVE LOGITS
     sufficient
    1.55
     suficiente
    1.48
     suficientes
    1.44
     adequate
    1.40
     documented
    1.39
     sufficiently
    1.35
     accessible
    1.28
    Sufficient
    1.28
     ausreichend
    1.27
     Sufficient
    1.27
    Activations Density 0.022%

    No Known Activations