© 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. 34-GEMMASCOPE-RES-131K
    7. 65105
    Prev
    Next
    INDEX
    Explanations

    copyright and location

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

    This neuron fires on tokens that are attribute‐style assignments—i.e. strings containing “=” such as HTML or server‐control attribute bindings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    chule
    -1.01
    textarea
    -0.93
    )}_{
    -0.93
     Paleozoic
    -0.84
    manufacturing
    -0.84
    ЭС
    -0.84
    ']),
    -0.83
     рассказать
    -0.83
    ardoor
    -0.82
    ressão
    -0.81
    POSITIVE LOGITS
     Location
    1.09
     loca
    0.94
     location
    0.93
    complement
    0.92
    Location
    0.89
     LOCATION
    0.85
     font
    0.84
     getLocation
    0.82
    Complement
    0.81
     Complement
    0.81
    Activations Density 0.000%

    No Known Activations