© 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. 10-GEMMASCOPE-RES-131K
    7. 111719
    Prev
    Next
    INDEX
    Explanations

    configuration details

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

    closing braces in structured code (JSON, JavaScript objects, or function definitions).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by numeric literal tokens (especially numbers and decimal‐point values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     if
    -2.61
     you
    -1.84
     there
    -1.83
     There
    -1.83
     because
    -1.82
     this
    -1.71
     even
    -1.69
     it
    -1.69
     so
    -1.68
     do
    -1.67
    POSITIVE LOGITS
    瞜
    1.88
     wacky
    1.86
     insanely
    1.83
     unbelievably
    1.83
     flashy
    1.79
     horrid
    1.74
     incont
    1.73
     mauva
    1.72
    ものが
    1.72
     inconce
    1.71
    Activations Density 0.005%

    No Known Activations