© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82444
    Prev
    Next
    INDEX
    Explanations

    end of file paths

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

    The neuron fires on code identifiers or keywords containing the substring “set,” for example in module or variable names like data_set, base_data_set, ParameterSet, etc.

    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
    ønne
    -0.86
    붓
    -0.77
     nests
    -0.75
     масте
    -0.74
    zionali
    -0.73
    Btw
    -0.73
     eux
    -0.72
     them
    -0.72
     crushes
    -0.71
    appareil
    -0.71
    POSITIVE LOGITS
    يكا
    0.74
    randrange
    0.73
    IMB
    0.73
    hede
    0.72
     :-)
    0.72
    垛
    0.71
    里面的
    0.71
     humble
    0.71
    れない
    0.71
    訕
    0.71
    Activations Density 0.025%

    No Known Activations