© 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. 71806
    Prev
    Next
    INDEX
    Explanations

    citations and academic references

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

    The neuron detects numbered reference or footnote citation markers (e.g. “[1]”, “[^2]”, “[B3]”) in academic‐style text.

    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
    辚
    -3.53
    ⁛
    -2.98
    ↵
    -2.95
    鶿
    -2.75
    ⽌
    -2.63
     stalling
    -2.56
    摭
    -2.45
    姈
    -2.42
     bekannte
    -2.39
    蚺
    -2.38
    POSITIVE LOGITS
    ],
    4.09
    },
    3.22
    y
    2.73
    ,
    2.66
    鋱
    2.55
     they
    2.53
    荩
    2.47
    ي
    2.42
    䊊
    2.42
    */
    2.39
    Activations Density 0.014%

    No Known Activations