© 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. 10-GEMMASCOPE-RES-131K
    7. 69579
    Prev
    Next
    INDEX
    Explanations

    counting objects or types

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

    The neuron activates strongly on numeric tokens and quantity expressions (e.g. digits, numeric counts, ranges).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     both
    -1.60
    0
    -1.44
    ↵↵
    -1.35
     kedua
    -1.32
     zugleich
    -1.22
    both
    -1.17
     entram
    -1.17
     BOTH
    -1.16
    penters
    -1.16
    ↵↵↵
    -1.16
    POSITIVE LOGITS
     AssemblyCompany
    1.27
     "}";
    1.24
    AutoScaleMode
    1.23
     the
    1.23
    fonds
    1.19
     it
    1.13
     альбо
    1.13
     in
    1.13
     vérité
    1.12
    omorphisms
    1.12
    Activations Density 0.121%

    No Known Activations