© 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. 107984
    Prev
    Next
    INDEX
    Explanations

    subject followed by action

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

    The neuron strongly activates on first-person pronouns and verbs in personal narrative contexts (e.g. “I,” “I’m,” “my,” “we”)—i.e. passages where the speaker is describing their own actions or experiences.

    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
    MIPS
    -0.98
     will
    -0.96
     odpově
    -0.96
    ]#
    -0.94
    比べると
    -0.93
     obrazov
    -0.92
     podróż
    -0.91
    pgfplots
    -0.91
     semble
    -0.91
     każdej
    -0.91
    POSITIVE LOGITS
     comes
    1.98
     goes
    1.98
     says
    1.62
     proceeds
    1.50
     gets
    1.49
     starts
    1.42
     decides
    1.41
     turns
    1.36
     decide
    1.32
     arrives
    1.32
    Activations Density 0.040%

    No Known Activations