© 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. 72683
    Prev
    Next
    INDEX
    Explanations

    localization and UI elements

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

    The neuron is triggered by identifiers in code that follow CamelCase or mixed-case naming conventions.

    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
    e
    -4.22
    c
    -3.69
     untuk
    -3.25
    All
    -3.23
    b
    -3.13
    h
    -3.05
     itſelf
    -3.05
    r
    -3.03
    When
    -3.02
    to
    -3.00
    POSITIVE LOGITS
    ☫
    3.36
    尨
    3.33
    辚
    3.31
    ፨
    3.13
    姈
    2.91
    
    2.66
     取り付け
    2.63
    艄
    2.55
    炁
    2.55
    媗
    2.53
    Activations Density 0.001%

    No Known Activations