© 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. 92059
    Prev
    Next
    INDEX
    Explanations

    Switching antipsychotics

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

    This neuron activates on the number 2 in various contexts, particularly when it appears in dates, versions, or numerical identifiers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    riott
    -0.85
     Ejecutivo
    -0.84
    ẳn
    -0.82
    IFYING
    -0.81
     déterminer
    -0.81
     Manten
    -0.79
    &:
    -0.79
    ęgn
    -0.79
     denke
    -0.77
    回避
    -0.77
    POSITIVE LOGITS
     dringend
    0.82
    タコ
    0.77
    男主
    0.75
     Punt
    0.71
    rical
    0.71
    看不
    0.71
     writes
    0.70
     Jury
    0.69
    sinx
    0.69
     worker
    0.69
    Activations Density 0.000%

    No Known Activations