© 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. 73650
    Prev
    Next
    INDEX
    Explanations

    punctuation and code elements

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

    the presence of standalone numeric tokens (numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     lại
    -1.44
     lenne
    -1.30
     уже
    -1.30
     seraient
    -1.19
     here
    -1.18
     già
    -1.14
     would
    -1.13
    อีก
    -1.13
     into
    -1.09
     estava
    -1.09
    POSITIVE LOGITS
     such
    1.48
     now
    1.46
    because
    1.34
     before
    1.30
     while
    1.28
     mientras
    1.25
     because
    1.24
     still
    1.23
     mentre
    1.22
     when
    1.13
    Activations Density 0.028%

    No Known Activations