© 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. 104235
    Prev
    Next
    INDEX
    Explanations

    beginning of phrases

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

    The neuron fires on the very first token of new paragraphs or major section openings.

    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
     also
    -1.99
     также
    -1.64
     також
    -1.55
     myös
    -1.52
     também
    -1.49
     גם
    -1.48
     także
    -1.43
     également
    -1.30
     نیز
    -1.28
     también
    -1.27
    POSITIVE LOGITS
     first
    1.60
    首先
    1.26
    unächst
    1.20
    Firstly
    1.13
     already
    1.13
    First
    1.09
     Bereits
    1.08
    さっそく
    1.08
    According
    1.05
    vious
    1.02
    Activations Density 0.106%

    No Known Activations