© 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. 76086
    Prev
    Next
    INDEX
    Explanations

    introducing additional items

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

    The neuron is triggered by commas marking list‐ or parenthesis‐style boundaries (and the surrounding noun phrases), i.e. it finds punctuation delimiting enumerations or asides.

    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
     or
    -1.20
    üğü
    -1.07
    旳
    -1.01
     waarop
    -0.96
     tedious
    -0.96
    glLoad
    -0.95
     that
    -0.95
    ᡥ
    -0.94
     gevonden
    -0.92
     when
    -0.92
    POSITIVE LOGITS
     including
    10.44
    including
    7.66
    Including
    7.38
    包括
    7.13
     Including
    7.00
     включая
    6.41
     INCLUDING
    6.09
     incluyendo
    6.06
     incluindo
    6.03
    INCLUDING
    5.38
    Activations Density 1.074%

    No Known Activations