© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73814
    Prev
    Next
    INDEX
    Explanations

    addition to and also

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

    The neuron fires on common multiword discourse markers and emphatic adverbial phrases (e.g. “Of course,” “In addition to,” “At least,” “It certainly,” “We understand very clearly”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     and
    -3.48
     that
    -2.34
     you
    -2.31
     with
    -2.00
     where
    -1.93
     your
    -1.84
     it
    -1.80
     to
    -1.75
    ertia
    -1.70
     part
    -1.68
    POSITIVE LOGITS
    8
    2.55
    9
    2.41
    2
    2.25
    5
    2.16
    7
    2.14
    0
    2.08
    1
    2.02
    Fakta
    1.99
    3
    1.97
    4
    1.94
    Activations Density 1.143%

    No Known Activations