© 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. 91813
    Prev
    Next
    INDEX
    Explanations

    pistol brace

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

    This neuron activates on numeric tokens and measurements (i.e. numbers and quantity expressions).

    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
    automated
    -0.83
     rerum
    -0.79
    Automated
    -0.78
    ﷽
    -0.75
     automated
    -0.75
    dusty
    -0.74
    しゃ
    -0.74
     automatic
    -0.72
     Remastered
    -0.69
     heated
    -0.69
    POSITIVE LOGITS
     stabilizing
    1.09
    ghost
    0.93
     ghost
    0.88
     стабили
    0.84
     stabilization
    0.84
     unser
    0.82
     Ledger
    0.82
     brace
    0.81
    stabili
    0.81
     stabilizer
    0.79
    Activations Density 0.022%

    No Known Activations