© 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. 22-GEMMASCOPE-RES-131K
    7. 38647
    Prev
    Next
    INDEX
    Explanations

    schema and definition

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

    The neuron fires chiefly on occurrences of the identifier or tag “Description.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ungef
    -1.00
     parallèle
    -0.96
    postIndex
    -0.93
     last
    -0.92
    habitude
    -0.91
     previous
    -0.91
    tended
    -0.90
    끗
    -0.90
    Notable
    -0.89
     percent
    -0.87
    POSITIVE LOGITS
    haled
    1.13
    quelize
    1.09
    uchtigkeit
    1.06
     TextAppearance
    1.02
    erobic
    1.00
     terbuka
    0.99
     describing
    0.98
     않
    0.98
    sistence
    0.97
     astore
    0.96
    Activations Density 0.077%

    No Known Activations