© 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. 20191
    Prev
    Next
    INDEX
    Explanations

    sling, mud-slinging, gunslinger

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

    The neuron fires on any token containing the character sequence “ling” (e.g. sling, slinging, shingle, flinger).

    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
     you
    -3.05
    0
    -2.94
    .
    -2.63
    7
    -2.45
     said
    -2.45
    艄
    -2.38
    9
    -2.22
    それを
    -2.16
    2
    -2.16
    //"
    -2.13
    POSITIVE LOGITS
    ]
    2.97
    ",
    2.77
     devising
    2.34
    ;
    2.20
    汌
    2.13
    蟜
    2.11
    至于
    2.08
    \'
    2.06
    ),
    2.06
     остров
    2.05
    Activations Density 0.002%

    No Known Activations