© 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. 69161
    Prev
    Next
    INDEX
    Explanations

    modules, vector spaces, and bundles

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

    This neuron fires on specialized algebraic and module‐theoretic terminology—words like “dimensional,” “simple,” “module(s),” “finitely,” “generated,” “Schur,” “lemma,” etc.

    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
     then
    -1.17
     use
    -1.13
     on
    -1.11
     and
    -1.05
    are
    -1.02
     અને
    -1.01
     running
    -1.01
    o
    -0.99
    me
    -0.98
     results
    -0.98
    POSITIVE LOGITS
    ческих
    1.29
    जब
    1.23
    Taille
    1.23
    ítica
    1.22
     odeur
    1.20
     terasa
    1.19
    PORTER
    1.18
    राज
    1.16
    entlich
    1.13
    Télé
    1.13
    Activations Density 0.030%

    No Known Activations