© 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. 33606
    Prev
    Next
    INDEX
    Explanations

    Directory, Inventories, History

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

    The neuron activates on any token containing the root “direct” (e.g. direct, Directory, DIRECTORIES).

    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
    umatic
    -0.79
     cál
    -0.74
    統
    -0.73
     العاده
    -0.72
    Pflege
    -0.71
    ден
    -0.69
     pledge
    -0.69
     Regierungs
    -0.68
     APPELL
    -0.68
    ibilidad
    -0.68
    POSITIVE LOGITS
    ory
    1.41
    tory
    1.19
    ORY
    1.05
     tory
    0.94
    ctory
    0.93
    ories
    0.93
    atory
    0.89
    Ory
    0.85
    itory
    0.84
    istory
    0.83
    Activations Density 0.083%

    No Known Activations