© 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. 102541
    Prev
    Next
    INDEX
    Explanations

    see and subsequent reference

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

    The neuron fires on occurrences of the word “see” used as a citation or cross-reference marker.

    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
    )
    -2.11
    ?
    -1.58
    ]
    -1.58
     dois
    -1.55
    ),
    -1.55
     sadece
    -1.54
    ripsi
    -1.52
    rofoam
    -1.48
    bbling
    -1.46
     los
    -1.45
    POSITIVE LOGITS
     our
    2.17
     the
    1.73
     illustrationer
    1.54
    袿
    1.52
    ㆆ
    1.52
     weiteres
    1.48
     below
    1.45
     your
    1.45
    antası
    1.42
     their
    1.38
    Activations Density 0.039%

    No Known Activations