© 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. 34-GEMMASCOPE-RES-131K
    4. 94063
    Prev
    Next
    INDEX
    Explanations

    answering machine voicemail

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

    The neuron fires on descriptive passages about phone-based voicemail messages (in particular, the promotional “One New Message” podcast segment).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     sustenance
    -0.89
     ort
    -0.82
     Ethio
    -0.80
     substan
    -0.80
    สบ
    -0.79
     bille
    -0.78
     signification
    -0.77
     relevan
    -0.77
     dimenti
    -0.76
     regu
    -0.75
    POSITIVE LOGITS
     message
    2.59
     voicemail
    2.33
     answering
    2.13
     Message
    2.06
    message
    2.02
     messages
    1.90
    Message
    1.87
    MESSAGE
    1.55
    essage
    1.52
    getMessage
    1.52
    Activations Density 0.026%

    No Known Activations