© 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. 77388
    Prev
    Next
    INDEX
    Explanations

    included in lists or categories

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

    The neuron fires on occurrences of the word “included” (especially in “included in” contexts).

    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
     cantidades
    -1.09
     sensaciones
    -1.09
     excelencia
    -1.07
     人
    -1.02
     emisiones
    -1.02
    gezogen
    -1.00
    férence
    -1.00
     utilisé
    -0.99
     shilling
    -0.98
     pozost
    -0.94
    POSITIVE LOGITS
     in
    3.23
     as
    1.59
     within
    1.48
     dalam
    1.39
     into
    1.36
     among
    1.32
     dans
    1.23
     on
    1.19
     amongst
    1.12
     nella
    1.11
    Activations Density 0.040%

    No Known Activations