© 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. 36529
    Prev
    Next
    INDEX
    Explanations

    continue direction

    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
    現在は
    -0.86
    PHONY
    -0.84
    imt
    -0.79
    ếm
    -0.79
    ங்கு
    -0.78
    petits
    -0.75
    Sziasztok
    -0.75
     spus
    -0.73
     atteint
    -0.73
     readiness
    -0.73
    POSITIVE LOGITS
     continue
    2.70
     continued
    2.67
    continue
    2.58
    继续
    2.58
     continues
    2.52
     still
    2.41
     continuing
    2.34
    continued
    2.11
     again
    2.08
     continuation
    2.00
    Activations Density 0.097%

    No Known Activations