© 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. 22-GEMMASCOPE-RES-131K
    4. 70991
    Prev
    Next
    INDEX
    Explanations

    forms and UI elements

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

    The neuron spots the central technical term or feature name in a question (e.g. “AddRange,” “model-driven,” “DisplayPort–D,” “reorderable list tile view,” etc.).

    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
    You
    -1.17
    This
    -1.16
    ):=\
    -1.13
     }^{
    -1.09
    ifornia
    -1.04
    }
    
    -1.04
    вана
    -1.04
    It
    -1.02
    ствует
    -1.02
     Automó
    -1.00
    POSITIVE LOGITS
    怎么回事
    1.05
     of
    1.02
    ぢ
    0.99
    使って
    0.97
     using
    0.95
    といいます
    0.94
    собенно
    0.93
    jà
    0.93
     автоматически
    0.93
     کنه
    0.90
    Activations Density 0.084%

    No Known Activations