© 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. 97799
    Prev
    Next
    INDEX
    Explanations

    version numbers, sha hashes

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

    The neuron strongly activates on colon punctuation (the “:” token).

    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
    
    -1.15
     its
    -1.10
     decora
    -1.05
    still
    -1.02
     paff
    -1.01
     Even
    -1.00
    tské
    -0.99
    stuffs
    -0.98
     ;"
    -0.97
    thirds
    -0.95
    POSITIVE LOGITS
    7
    1.19
    8
    1.17
    1.13
    9
    1.12
    5
    1.04
     Respuesta
    1.02
     particolarmente
    1.01
     ressemble
    1.00
    4
    1.00
     sabo
    0.98
    Activations Density 0.002%
    No Known Activations