© 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. 10-GEMMASCOPE-RES-131K
    7. 101218
    Prev
    Next
    INDEX
    Explanations

    release of information

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

    The neuron responds to words about releasing, disclosing, or making public official documents or numerical data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    <
    -1.38
     I
    -1.38
    :
    -1.24
     /
    -1.20
    -
    -1.15
     właści
    -1.12
    2
    -1.09
    :{
    -1.07
     <
    -1.07
    ocities
    -1.06
    POSITIVE LOGITS
     why
    1.30
     tangerang
    1.28
    ༀ
    1.24
    ၶ
    1.16
     faptul
    1.16
    ישראל
    1.12
    倻
    1.11
     dată
    1.09
    نة
    1.09
     MINNESOTA
    1.09
    Activations Density 0.131%

    No Known Activations