© 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. 103232
    Prev
    Next
    INDEX
    Explanations

    specific nouns

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

    The neuron strongly activates on unusually long single-word tokens (i.e. lengthy words).

    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
     mainly
    -1.41
     specially
    -1.39
     specifically
    -1.30
     principally
    -1.30
     primarily
    -1.29
     mostly
    -1.28
     Particularly
    -1.27
     not
    -1.26
     irrespective
    -1.26
     because
    -1.23
    POSITIVE LOGITS
     Dinas
    1.27
     revered
    1.25
    ïe
    1.23
    irée
    1.21
     vores
    1.18
    ειτουργ
    1.18
     cyclisme
    1.17
     joyous
    1.15
     rahat
    1.14
    tovers
    1.13
    Activations Density 0.858%

    No Known Activations