© 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. 396
    Prev
    Next
    INDEX
    Explanations

    deep, rich, booming voice

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

    The main thing this neuron does is detect numeric tokens or numerical information (e.g. digits and statistics) in the text.

    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
     sque
    -1.05
    eeeeeeee
    -0.77
    Loft
    -0.77
     shriek
    -0.74
    IntOverflow
    -0.74
     scream
    -0.71
    ENODE
    -0.71
    Ỷ
    -0.70
     Violin
    -0.70
     screamed
    -0.69
    POSITIVE LOGITS
     deep
    3.25
    deep
    2.70
    Deep
    2.41
     Deep
    2.36
     deeper
    2.28
     deepened
    2.13
     low
    2.13
     deepen
    2.09
     deepest
    2.08
     profundo
    2.06
    Activations Density 0.031%

    No Known Activations