© 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. 22-GEMMASCOPE-RES-131K
    7. 73327
    Prev
    Next
    INDEX
    Explanations

    dictionary or dict

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

    The neuron strongly activates on the tokens “dictionary” or “dict,” i.e. when the text names or tags a dictionary-like data structure.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    actéristi
    -2.92
     haupts
    -2.84
    abatic
    -2.67
    ឵
    -2.63
     he
    -2.56
     ähnliche
    -2.53
     cuyos
    -2.42
     каждой
    -2.42
     letzten
    -2.41
     новые
    -2.38
    POSITIVE LOGITS
    \
    3.41
    狆
    2.75
    ”،
    2.52
     itſelf
    2.39
    "،
    2.38
     plis
    2.33
     SPAIN
    2.31
     используется
    2.27
     bruges
    2.25
     jaja
    2.16
    Activations Density 0.011%

    No Known Activations