© 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. 39872
    Prev
    Next
    INDEX
    Explanations

    classic followed by a descriptor

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

    The neuron responds strongly to occurrences of the word “classic” (in any casing).

    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
    
    -2.92
    虓
    -2.77
    埛
    -2.66
    
    -2.66
    簠
    -2.53
    蜮
    -2.50
    釤
    -2.50
    嫑
    -2.47
     preſent
    -2.47
     ridiculously
    -2.45
    POSITIVE LOGITS
    i
    3.30
    M
    3.11
    C
    3.08
    L
    3.02
    F
    3.00
    You
    2.94
    A
    2.89
    as
    2.89
    g
    2.75
    w
    2.75
    Activations Density 0.013%

    No Known Activations