© 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. 22-GEMMASCOPE-RES-131K
    7. 577
    Prev
    Next
    INDEX
    Explanations

    said that

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

    This neuron flags first-person self-references, especially instances of “I” (and accompanying verbs) describing the speaker’s own actions.

    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
    あなたは
    -1.16
     you
    -1.07
     a
    -0.96
     from
    -0.96
     each
    -0.88
    あなた
    -0.86
     sigui
    -0.85
    ناصر
    -0.85
    その後
    -0.85
     every
    -0.84
    POSITIVE LOGITS
     flere
    1.03
     onBackPressed
    0.99
    ﻨ
    0.96
     to
    0.95
    мери
    0.93
    Manfaat
    0.91
     角色
    0.90
     Can
    0.89
     降
    0.89
     my
    0.88
    Activations Density 0.014%

    No Known Activations