© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58761
    Prev
    Next
    INDEX
    Explanations

    search results pages

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

    The neuron fires on occurrences of the phrase “search results,” especially when it’s followed by a numeric count.

    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
     However
    -1.77
    }
    
    -1.70
     jika
    -1.70
    ,
    
    -1.58
    虽然
    -1.56
     Kemudian
    -1.56
     then
    -1.55
    但是
    -1.52
    }}
    -1.46
     If
    -1.44
    POSITIVE LOGITS
     secado
    1.73
    在哪里
    1.59
     entendido
    1.56
    箆
    1.56
     típica
    1.52
    獃
    1.52
    所说的
    1.51
    NESSEE
    1.49
     colorido
    1.48
     masaje
    1.47
    Activations Density 0.026%

    No Known Activations