© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64587
    Prev
    Next
    INDEX
    Explanations

    something + pronoun subject

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

    This neuron detects abstract indefinite and demonstrative pronouns—especially the word “something” (and similar words like “that,” “this,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    -1.39
     bieber
    -1.23
    ulity
    -1.15
    isesta
    -1.13
    אין
    -1.10
    %);
    -1.09
    acheter
    -1.05
    ubov
    -1.05
    AFFIRMED
    -1.05
    endurch
    -1.04
    POSITIVE LOGITS
     you
    2.61
     we
    2.44
     they
    1.89
     I
    1.86
     everyone
    1.76
     that
    1.66
     of
    1.52
     يجب
    1.40
    everyone
    1.37
     naszej
    1.35
    Activations Density 0.009%

    No Known Activations