© 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. 34-GEMMASCOPE-RES-131K
    7. 30908
    Prev
    Next
    INDEX
    Explanations

    future commitment and expectation

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

    The neuron is looking for personal‐reference words and pronouns—particularly relative and second-person pronouns (e.g. “who,” “you,” “your,” “me”) that introduce or refer to people.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    нибудь
    -0.99
     ज्यादा
    -0.95
    zanne
    -0.94
    ícias
    -0.90
     außergewöhn
    -0.88
     fallait
    -0.83
     éton
    -0.81
    ТВ
    -0.80
     जर
    -0.79
    ALIAN
    -0.77
    POSITIVE LOGITS
     hoped
    1.89
    好不容易
    1.84
     invested
    1.70
     promising
    1.66
     hopes
    1.60
    楽しみにして
    1.59
    せっかく
    1.53
     promised
    1.52
     planned
    1.51
     expectation
    1.37
    Activations Density 0.078%

    No Known Activations