© 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. 73388
    Prev
    Next
    INDEX
    Explanations

    version numbers and licenses

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

    The neuron detects formal reference and citation markers (e.g. legal case terms like “Reversed”/“appellant,” editorial notes like “sic,” Roman-numeral volume indicators, license/version labels).

    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
    escence
    -0.89
    cticide
    -0.89
     περι
    -0.85
     haremos
    -0.85
    })+
    -0.84
    شنبه
    -0.84
    gdala
    -0.84
     Unexpected
    -0.82
    jén
    -0.80
     VOC
    -0.80
    POSITIVE LOGITS
     at
    1.16
    </em>
    1.02
    žem
    0.98
    .,
    0.93
     efficaces
    0.85
     ruinas
    0.84
    Ib
    0.82
    ांस
    0.82
     لكل
    0.78
    .
    0.78
    Activations Density 0.010%

    No Known Activations