© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66640
    Prev
    Next
    INDEX
    Explanations

    year digits

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

    The neuron detects standalone multi-digit numeric sequences (e.g. three-digit page or citation numbers) in legal citation contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     of
    -2.45
     and
    -1.84
     with
    -1.72
     at
    -1.59
     before
    -1.48
     vernis
    -1.42
     händer
    -1.42
     or
    -1.40
    Putting
    -1.40
     memen
    -1.39
    POSITIVE LOGITS
    r
    1.78
     myriad
    1.62
     extremely
    1.60
     "
    1.57
    st
    1.55
    n
    1.55
     exceptional
    1.53
     exceptionally
    1.51
    ..........
    1.47
    u
    1.44
    Activations Density 0.004%

    No Known Activations