© 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. 10-GEMMASCOPE-RES-131K
    4. 68842
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and keywords

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

    The neuron specifically lights up on programming identifier tokens—names of types, functions, methods, or variables (e.g. CamelCase or snake_case code symbols).

    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
     of
    -1.62
     which
    -1.49
     their
    -1.28
     as
    -1.20
     with
    -1.17
     antichi
    -1.16
     but
    -1.12
     all
    -1.09
     them
    -1.09
    後は
    -1.09
    POSITIVE LOGITS
    鸲
    1.25
    FONTE
    1.22
     таких
    1.22
    asthan
    1.17
     portatil
    1.17
    另一
    1.16
    乄
    1.16
     améli
    1.16
    Etiquetas
    1.15
     something
    1.14
    Activations Density 0.039%

    No Known Activations