© 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. 34-GEMMASCOPE-RES-131K
    4. 48400
    Prev
    Next
    INDEX
    Explanations

    bitwise OR or pipe separator

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

    The neuron flags all‐caps identifiers (macros or named constants/flags) in code.

    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
     outono
    -0.99
    arabe
    -0.98
    שוב
    -0.91
    beqa
    -0.88
     előtt
    -0.84
     themselves
    -0.83
     Denken
    -0.83
    自身
    -0.82
     until
    -0.82
     Ultimately
    -0.82
    POSITIVE LOGITS
     |
    2.06
    |
    1.91
     |
    
    1.38
    ∣
    1.27
    |\
    1.27
    |$
    1.18
     |\
    1.18
    |"
    1.13
    |'
    1.13
     ।
    1.09
    Activations Density 0.036%

    No Known Activations