© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44963
    Prev
    Next
    INDEX
    Explanations

    legal citations or code comments

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

    The neuron fires on the form field label “Zip,” i.e. when a postal‐code entry field is present.

    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
    j
    -2.09
    n
    -1.93
    u
    -1.92
    t
    -1.80
    x
    -1.70
    ll
    -1.64
    m
    -1.59
    i
    -1.58
    h
    -1.54
    q
    -1.53
    POSITIVE LOGITS
     mentale
    1.75
     minimale
    1.67
    LoL
    1.66
     mesurer
    1.64
    PERFECT
    1.62
     nye
    1.60
    anyway
    1.60
    macOS
    1.59
    锨
    1.59
     fatale
    1.57
    Activations Density 0.000%

    No Known Activations