© 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. 85391
    Prev
    Next
    INDEX
    Explanations

    seawater, ClassName, nightlife, favicon

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

    The neuron fires on single tokens that are internally composed of two smaller words joined together (e.g. seawater, nightlife, ClassName) – in other words, compound words.

    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
    ation
    -2.67
    }
    -2.44
    er
    -2.39
    ’
    -2.34
    '>
    -2.23
    ᠂
    -2.22
    '
    -2.09
     苗
    -2.06
    『
    -2.03
    .'
    -2.00
    POSITIVE LOGITS
     Not
    2.17
    𓆜
    2.17
     They
    2.14
    ｷ
    2.14
    ．．．
    2.13
    嘞
    2.13
     tidak
    2.09
    我认为
    2.09
    ＾＾；
    2.00
    って思
    1.99
    Activations Density 0.006%

    No Known Activations