© 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. 1703
    Prev
    Next
    INDEX
    Explanations

    mines and flags

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

    The neuron fires on code snippets that define database schema fields—especially Android Room entity annotations (e.g. @Entity, @PrimaryKey, @ColumnInfo) and the accompanying `val` declarations.

    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
    ropolitan
    -0.92
    CTION
    -0.88
    keywords
    -0.79
    ARCH
    -0.78
    ат
    -0.76
     酷
    -0.73
    ACION
    -0.72
    钥
    -0.70
    Partido
    -0.69
     warmest
    -0.69
    POSITIVE LOGITS
     mines
    1.48
     Mines
    1.32
     mine
    1.27
    Mines
    1.26
    mines
    1.25
     bomb
    1.24
     bombs
    1.23
     flags
    1.23
     reveal
    1.20
    Mine
    1.17
    Activations Density 0.002%

    No Known Activations