© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49001
    Prev
    Next
    INDEX
    Explanations

    Sam or Samuel names

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

    The neuron strongly activates on occurrences of the string “Sam” (as in names or handles, e.g. “Sam,” “Samuel,” or “Sam Lantinga”)—in other words, it’s detecting that specific name token.

    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
    カリ
    -0.79
     kinds
    -0.77
     relevant
    -0.74
     regards
    -0.73
    THURSDAY
    -0.73
    incere
    -0.73
    kinds
    -0.72
     overzicht
    -0.72
     گرف
    -0.71
     béo
    -0.71
    POSITIVE LOGITS
    Sam
    1.16
     Sam
    1.12
    Chord
    0.94
     Chord
    0.93
    SAM
    0.92
     SAM
    0.90
     Samantha
    0.87
    sam
    0.86
     سام
    0.81
     Samuel
    0.79
    Activations Density 0.043%

    No Known Activations