© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102073
    Prev
    Next
    INDEX
    Explanations

    bloom and variations

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

    The neuron strongly activates on any token containing the sequence “bloom” (e.g. Bloom, blooms, bloomfield, bloomers).

    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
    歘
    -3.36
    泐
    -3.30
    
    -3.13
    咈
    -3.06
    蓠
    -3.03
    肏
    -3.00
    镚
    -2.97
    袿
    -2.95
    婼
    -2.94
    }
    -2.89
    POSITIVE LOGITS
    {
    3.92
    ]
    3.91
    (
    3.84
    “
    3.77
    ;
    3.73
    )
    3.25
    *
    3.09
    .
    2.91
     If
    2.89
    ?
    2.89
    Activations Density 0.002%

    No Known Activations