© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117068
    Prev
    Next
    INDEX
    Explanations

    quoted descriptions or states

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

    The neuron is activated by the presence of direct‐speech markers—quotation marks and the words framed by them.

    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
     during
    -2.64
     after
    -2.61
     before
    -2.53
     with
    -2.48
     because
    -2.44
     when
    -2.38
     while
    -2.25
     that
    -2.11
     on
    -2.09
     this
    -2.05
    POSITIVE LOGITS
    probably
    2.19
    quite
    2.02
     gigantic
    1.98
     .......
    1.95
     exceedingly
    1.95
     soooo
    1.94
     specif
    1.89
    mainly
    1.88
     remarkably
    1.88
     sooo
    1.88
    Activations Density 0.041%

    No Known Activations