© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130653
    Prev
    Next
    INDEX
    Explanations

    not only ... also

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

    This neuron fires on third-person subject pronouns (especially “it,” “they,” or “there”) when they introduce or continue a statement.

    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
     که
    -1.82
    section
    -1.35
    }};
    -1.32
    []{"
    -1.30
     mainly
    -1.28
    ests
    -1.27
     ktore
    -1.27
    ="
    -1.25
    text
    -1.23
    mbols
    -1.23
    POSITIVE LOGITS
     sogar
    1.57
     also
    1.48
     gesamten
    1.47
     uſed
    1.44
     même
    1.41
    就连
    1.39
     The
    1.38
    ꒥
    1.38
     immobili
    1.32
    当たり前
    1.31
    Activations Density 0.013%

    No Known Activations