© 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. 84099
    Prev
    Next
    INDEX
    Explanations

    origin, destination, route, address, coordinates

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

    The neuron fires on code‐like identifiers and field/property names (e.g. class, model, JSON key, or database column names).

    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
     hidratante
    -1.46
     возможность
    -1.35
     bailarina
    -1.32
     grasas
    -1.27
     who
    -1.26
    艹
    -1.18
    gangen
    -1.17
    罫
    -1.15
    利率
    -1.14
     work
    -1.13
    POSITIVE LOGITS
    頜
    1.52
    颚
    1.44
     destination
    1.42
     location
    1.41
     zondag
    1.27
    なのだ
    1.23
    卫生间
    1.23
     city
    1.22
     locations
    1.21
    艏
    1.21
    Activations Density 0.017%

    No Known Activations