© 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. 48191
    Prev
    Next
    INDEX
    Explanations

    edge or border of an object

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

    The neuron fires strongly on mentions of “rim” (and related references to circular borders or edges of objects).

    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
    獃
    -2.77
    
    -2.66
     玲
    -2.64
    ௗ
    -2.48
    In
    -2.45
    an
    -2.42
    ઁ
    -2.36
    ]');
    -2.36
    $};
    -2.34
    瀦
    -2.33
    POSITIVE LOGITS
    皤
    2.98
    臜
    2.64
    很重要
    2.39
     '
    2.25
     rim
    2.23
     abbildung
    2.22
     retten
    2.19
     участники
    2.17
    ll
    2.16
    ні
    2.16
    Activations Density 0.005%

    No Known Activations