© 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. 81061
    Prev
    Next
    INDEX
    Explanations

    whether to buy or sell

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

    This neuron responds to high-level document-structure markers—especially headings and punctuation that denote section boundaries.

    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
     alltså
    -1.38
     hoga
    -1.22
     this
    -1.20
     xxiii
    -1.17
     xxiv
    -1.16
     xxii
    -1.13
     xxvi
    -1.10
     also
    -1.08
     liknande
    -1.07
     xviii
    -1.05
    POSITIVE LOGITS
     whether
    2.31
    Whether
    2.17
    Are
    2.11
     Whether
    1.98
    If
    1.91
     Are
    1.88
     if
    1.84
    Many
    1.80
     everyone
    1.80
     your
    1.76
    Activations Density 0.183%

    No Known Activations