© 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. 22-GEMMASCOPE-RES-131K
    7. 14128
    Prev
    Next
    INDEX
    Explanations

    photo gallery

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

    The neuron activates on occurrences of the word “gallery” (in any casing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    NOSIS
    -3.08
    餿
    -2.86
    rowable
    -2.78
    皛
    -2.69
    焿
    -2.61
    ⢧
    -2.59
    鹛
    -2.59
     شیپور
    -2.58
    
    -2.41
     搞笑
    -2.39
    POSITIVE LOGITS
    ]
    3.09
    )
    2.81
     of
    2.67
    "
    2.61
    :
    2.23
    ;
    2.22
    ’
    2.20
     unwavering
    2.03
     haciendo
    2.00
    ?
    2.00
    Activations Density 0.022%

    No Known Activations