© 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. 34-GEMMASCOPE-RES-131K
    7. 110998
    Prev
    Next
    INDEX
    Explanations

    marty names and martyrs

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

    This neuron fires on any token containing the substring “mart” (e.g. martyr, Marty, Martyrs).

    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
    ENDO
    -0.85
    мир
    -0.83
    ës
    -0.82
    toi
    -0.78
    Edits
    -0.77
     huy
    -0.76
    itya
    -0.75
    IBLE
    -0.74
     conquer
    -0.74
    Pine
    -0.74
    POSITIVE LOGITS
     *}$
    0.80
     vinculado
    0.75
    ッシ
    0.71
    됐
    0.70
     chun
    0.70
    burnt
    0.70
     verbeter
    0.69
    θέ
    0.69
     elimination
    0.69
     marty
    0.69
    Activations Density 0.027%

    No Known Activations