© 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. 72712
    Prev
    Next
    INDEX
    Explanations

    some someone

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

    The neuron fires on indefinite references—especially “some,” “someone,” and similar pronouns indicating unspecified persons or quantities.

    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
     at
    -1.76
     on
    -1.62
     no
    -1.58
     let
    -1.46
     new
    -1.45
    眼下
    -1.42
     gehad
    -1.38
     of
    -1.37
     after
    -1.37
     waarop
    -1.33
    POSITIVE LOGITS
     sprüche
    2.17
    𓆏
    1.84
    庒
    1.82
    鶫
    1.79
     niedersachsen
    1.73
    慙
    1.73
     anhänger
    1.66
    often
    1.66
    鰱
    1.65
    羮
    1.63
    Activations Density 0.078%

    No Known Activations