© 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. 22-GEMMASCOPE-RES-131K
    4. 73698
    Prev
    Next
    INDEX
    Explanations

    places and communities

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

    The neuron consistently activates on nouns denoting broad collective contexts or settings—social groups, environments, institutions, or locations (e.g. family, societies, markets, terrain, district, building).

    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
     就
    -1.34
     to
    -1.23
    以及
    -1.16
     as
    -1.15
     being
    -1.12
     its
    -1.09
     mancanza
    -1.05
     invites
    -1.02
     oraz
    -1.01
     for
    -1.00
    POSITIVE LOGITS
     that
    1.63
    ที่มี
    1.29
     where
    1.28
     of
    1.08
     somme
    1.05
     whose
    1.05
     which
    1.04
     with
    1.02
     burbu
    1.01
    今度
    0.96
    Activations Density 0.105%

    No Known Activations