© 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. 21283
    Prev
    Next
    INDEX
    Explanations

    hexagon, hexagonal, hex grid

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

    This neuron detects mentions of “hexagon” (and related hexagonal shape) terminology in the text.

    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
    ”
    -2.95
    “
    -2.44
    }
    -2.42
    ,”
    -2.39
    ↵↵
    -2.22
    盌
    -2.11
    -“
    -2.08
    :”
    -2.08
     новое
    -2.05
     alugar
    -2.05
    POSITIVE LOGITS
     After
    2.19
    嗚
    2.08
     Following
    2.08
     Hex
    2.05
    section
    1.98
    七夕
    1.95
    ⃣
    1.92
     lograr
    1.91
    徘
    1.90
    硖
    1.90
    Activations Density 0.028%

    No Known Activations