© 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. 31487
    Prev
    Next
    INDEX
    Explanations

    firsthand knowledge and understanding

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

    The neuron strongly activates on self-referential declarations, especially first-person pronouns (“I,” “we”) and statements of personal experience or assurance.

    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
     escond
    -1.08
     mér
    -1.08
    itrile
    -1.04
    dieu
    -0.96
    PHPExcel
    -0.94
    ResourceBundle
    -0.94
     váll
    -0.93
     Dental
    -0.93
    --;
    -0.92
     ]
    -0.91
    POSITIVE LOGITS
     understands
    2.61
     understand
    2.58
     knows
    2.38
     know
    2.34
     understanding
    2.08
     familiarity
    2.03
     firsthand
    1.81
    Understand
    1.75
    understand
    1.70
     Understand
    1.70
    Activations Density 0.063%

    No Known Activations