© 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. 66626
    Prev
    Next
    INDEX
    Explanations

    your + product/service indicator

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

    This neuron detects direct second-person address words (especially “you” and “your”) that speak straight to the reader.

    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
     ambul
    -1.00
    p
    -0.99
     is
    -0.99
     projection
    -0.96
    w
    -0.95
    c
    -0.93
    m
    -0.93
    醍
    -0.93
    //...
    -0.92
     output
    -0.92
    POSITIVE LOGITS
     první
    1.17
    ﮯ
    1.14
     számára
    1.12
    €“
    1.08
     ulub
    1.05
     tujuh
    1.05
     rád
    1.04
    favorite
    1.03
     pieles
    1.03
     zelfs
    1.02
    Activations Density 0.093%

    No Known Activations