© 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. 22-GEMMASCOPE-RES-131K
    7. 12932
    Prev
    Next
    INDEX
    Explanations

    list of items and their properties

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

    The neuron fires on multi‐word code identifiers and API/resource names (e.g. class, page, service, policy, or controller names in CamelCase or snake_case).

    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
     बजाय
    -1.26
    Crítica
    -1.13
     vermutlich
    -1.13
     Ambos
    -1.12
     Both
    -1.11
    Curios
    -1.09
     decret
    -1.08
     Despite
    -1.07
     Beide
    -1.06
     Although
    -1.05
    POSITIVE LOGITS
    之以
    1.21
    ₱
    1.20
     muebles
    1.19
     чехол
    1.19
     personalización
    1.18
    ۴
    1.18
     mensaj
    1.16
     contactez
    1.16
     fabriqué
    1.16
    ٣
    1.16
    Activations Density 0.075%

    No Known Activations