© 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. 34-GEMMASCOPE-RES-131K
    4. 50499
    Prev
    Next
    INDEX
    Explanations

    introducing explanations and examples

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

    This neuron lights up on occurrences of the discourse cue “Here” (especially sentence-initial “Here,” or “Here is/are”) indicating a transition or presentation.

    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
     which
    -1.20
    complish
    -1.13
     هذا
    -1.09
    inerary
    -0.99
    暟
    -0.96
    һ
    -0.95
     obec
    -0.92
     keinerlei
    -0.90
     Fasting
    -0.88
    ᐕ
    -0.88
    POSITIVE LOGITS
     again
    1.93
     we
    1.84
    ,
    1.73
     too
    1.59
     you
    1.52
    Again
    1.51
     is
    1.44
     are
    1.43
     it
    1.35
     снова
    1.17
    Activations Density 0.028%

    No Known Activations