© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75163
    Prev
    Next
    INDEX
    Explanations

    looking forward to

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

    The neuron fires strongly on the “look forward to” (and “looking forward to”) phrase expressing anticipation.

    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
    柘
    -1.47
    reathe
    -1.45
    ichtete
    -1.45
    VNB
    -1.41
     disesuaikan
    -1.41
    олові
    -1.40
     encompassed
    -1.40
    geox
    -1.39
    eclamp
    -1.38
    ullable
    -1.36
    POSITIVE LOGITS
    ridescent
    1.79
    你
    1.53
    FL
    1.47
    BE
    1.45
    BY
    1.42
    return
    1.41
    RI
    1.39
     namens
    1.38
    to
    1.38
    </u>
    1.35
    Activations Density 0.004%

    No Known Activations