© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128066
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numeric temperature mentions in degrees Celsius.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    degrees C

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     that
    -1.66
     you
    -1.24
     our
    -1.17
     That
    -1.13
     which
    -1.02
    те
    -1.01
     direttamente
    -1.01
                
    -0.99
    }
    -0.98
     also
    -0.96
    POSITIVE LOGITS
    wendig
    1.04
     ruidos
    1.02
    Hilsen
    0.99
    Затем
    0.99
    ıcı
    0.99
    Betyg
    0.99
    Materiale
    0.98
     població
    0.97
     getopt
    0.97
    ricate
    0.97
    Activations Density 0.007%

    No Known Activations