© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1282
    Prev
    Next
    INDEX
    Explanations

    state uncertainty

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

    The main thing this neuron does is pick out technical tokens and numeric identifiers—e.g. key terms like “state,” version numbers, model names, and other digits or domain‐specific jargon.

    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
    卿
    -0.77
    ridis
    -0.71
     Pich
    -0.71
    MigrationBuilder
    -0.70
     tslint
    -0.68
    ้าย
    -0.68
     αρ
    -0.67
    回収
    -0.67
    صح
    -0.66
     fréquent
    -0.66
    POSITIVE LOGITS
     observation
    1.99
     state
    1.85
    Observation
    1.77
     observations
    1.74
     Observation
    1.69
    observation
    1.66
    state
    1.51
    OBSERV
    1.43
     Observations
    1.40
     OBSERV
    1.39
    Activations Density 0.011%

    No Known Activations