© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7205
    Prev
    Next
    INDEX
    Explanations

    :: type or module access

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

    The neuron is specialized to spot the “::” token (the double-colon operator), as used in type annotations or namespace/scoping expressions.

    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
    ︕
    -2.23
    بوت
    -2.22
     expanse
    -2.13
     ไอ
    -2.06
    饃
    -2.02
     ハロウィン
    -2.00
    tamaris
    -1.94
     壁纸
    -1.94
    髏
    -1.94
    婓
    -1.91
    POSITIVE LOGITS
     '
    2.59
    ro
    2.50
    h
    2.41
    as
    2.28
     /
    2.17
     –
    2.14
    斟
    2.14
    tion
    2.14
     -
    2.11
     are
    2.09
    Activations Density 0.013%

    No Known Activations