© 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. 80775
    Prev
    Next
    INDEX
    Explanations

    hashtag components

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

    The neuron detects named entities and hashtags—that is, capitalized brand/event names and “#” tags.

    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
     it
    -1.45
     as
    -1.41
     and
    -1.37
     without
    -1.33
     with
    -1.23
     for
    -1.14
     an
    -1.13
     two
    -1.13
     three
    -1.11
     Two
    -1.09
    POSITIVE LOGITS
     #
    1.69
    /#
    1.58
    ,#
    1.55
     hashtag
    1.51
    たぶん
    1.42
    顚
    1.39
    だいたい
    1.39
     diriger
    1.34
    ">#
    1.30
     savag
    1.29
    Activations Density 0.012%

    No Known Activations