© 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. 34-GEMMASCOPE-RES-131K
    7. 117873
    Prev
    Next
    INDEX
    Explanations

    mind and consciousness

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

    The neuron is responding to very high‐frequency tokens—mostly common function words and other extremely frequent terms.

    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
     deposit
    -1.29
     deposits
    -1.27
     DEPOSIT
    -1.11
     Deposit
    -1.05
     Deposits
    -0.97
     deposited
    -0.90
    Deposits
    -0.87
    Deposit
    -0.85
    deposit
    -0.84
     DEPOS
    -0.84
    POSITIVE LOGITS
     mind
    3.20
     intellect
    2.92
     minds
    2.34
    mind
    2.06
     intelligence
    1.99
     Mind
    1.85
     consciousness
    1.76
     MIND
    1.70
    Mind
    1.70
    intel
    1.66
    Activations Density 0.021%

    No Known Activations