© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58304
    Prev
    Next
    INDEX
    Explanations

    ensure a state or action

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

    The neuron detects personal‐agency function words—especially first‐ and second‐person pronouns (we, our, you) and related forms.

    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
    mpagne
    -1.93
    }
    -1.84
     for
    -1.81
    ⎆
    -1.80
     "...
    -1.79
     önem
    -1.74
     but
    -1.71
     asiático
    -1.66
    ܼ
    -1.64
    geſ
    -1.63
    POSITIVE LOGITS
    柺
    1.81
    ஂ
    1.70
     ambayo
    1.68
     agrico
    1.67
    j
    1.62
     zalando
    1.62
    which
    1.60
    踅
    1.59
     Glied
    1.59
     decorativa
    1.59
    Activations Density 0.014%

    No Known Activations