© 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. 34-GEMMASCOPE-RES-131K
    4. 50014
    Prev
    Next
    INDEX
    Explanations

    design patterns and code components

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

    The neuron activates on capitalized identifier tokens that are part of class, type, or other named declarations in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     soprattutto
    -1.37
     especially
    -1.21
     особенно
    -1.18
     particularmente
    -1.16
     Especially
    -1.12
                                   
    -1.06
     zwłaszcza
    -1.04
     betreffende
    -1.03
     Особенно
    -1.03
     özellikle
    -1.01
    POSITIVE LOGITS
     museo
    1.30
     residencial
    1.23
    Suka
    1.20
     extenso
    1.19
     nyeri
    1.16
     paja
    1.13
     pantalones
    1.11
     atle
    1.10
     korban
    1.10
    !!
    1.10
    Activations Density 0.032%

    No Known Activations