© 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. 104309
    Prev
    Next
    INDEX
    Explanations

    conveying a message

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

    The neuron fires strongly on occurrences of the word “message,” especially when it introduces or highlights a communicated theme.

    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
     decoradas
    -1.36
     wußte
    -1.35
     ließen
    -1.35
     большого
    -1.29
     mecanismos
    -1.27
    </strong>
    -1.23
     большое
    -1.20
     weisen
    -1.20
     guapos
    -1.20
    䊐
    -1.20
    POSITIVE LOGITS
     that
    1.95
     message
    1.90
     Messages
    1.70
     messages
    1.70
     Botschaft
    1.64
     Message
    1.53
     about
    1.48
     MESSAGE
    1.46
    messages
    1.45
     messaggio
    1.45
    Activations Density 0.010%

    No Known Activations