© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20919
    Prev
    Next
    INDEX
    Explanations

    one of a kind

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

    The neuron specifically detects the phrase “one of a kind” (often hyphenated).

    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
    \
    -2.39
    3
    -2.05
    0
    -2.03
    </i>
    -1.83
    to
    -1.80
    by
    -1.73
                    
    -1.70
    >
    -1.65
    ;
    
    -1.65
     ponemos
    -1.58
    POSITIVE LOGITS
    tieve
    1.98
    灃
    1.93
    ciones
    1.84
    служба
    1.81
    푢
    1.78
     sisält
    1.76
    未完
    1.75
    φάλ
    1.74
    ógicos
    1.73
     encompassing
    1.73
    Activations Density 0.004%

    No Known Activations