© 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. 34-GEMMASCOPE-RES-131K
    7. 30010
    Prev
    Next
    INDEX
    Explanations

    backup and reinforcements

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

    The neuron strongly activates on standalone multi‐digit numeric tokens (i.e. integer counts or measurements).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    paku
    -0.87
    
    -0.86
    ställning
    -0.84
    widual
    -0.83
    ⒏
    -0.82
     halte
    -0.80
    改为
    -0.79
    ppled
    -0.79
    idee
    -0.79
    glLoad
    -0.78
    POSITIVE LOGITS
     reinforcements
    4.78
     reinforcement
    3.98
     reinforce
    3.08
     Reinforcement
    2.88
     backup
    2.83
    rein
    2.69
    Rein
    2.69
     refuer
    2.67
     reinforcing
    2.63
     Verstär
    2.59
    Activations Density 0.026%

    No Known Activations