© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84314
    Prev
    Next
    INDEX
    Explanations

    Copyright, #include, Electroretinographic, Houston Dynamo

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

    This neuron specifically activates on the token “summer,” as seen in the occurrences of “summer” in event names.

    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
    noons
    -1.19
    了自己
    -1.14
     even
    -1.10
    mappedBy
    -1.05
    AuthContext
    -1.04
     estime
    -1.04
     it
    -1.04
    yship
    -1.02
     évé
    -1.02
     relata
    -1.02
    POSITIVE LOGITS
    Después
    1.05
    sproble
    1.04
    Dopo
    0.98
    テイ
    0.97
     nimmer
    0.96
    Similar
    0.95
     gånger
    0.95
    𓂂
    0.92
    味付け
    0.91
     förb
    0.90
    Activations Density 0.000%

    No Known Activations