© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69042
    Prev
    Next
    INDEX
    Explanations

    command line flags and options

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

    The neuron fires on command‐line option tokens (i.e. hyphen-prefixed flags).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     mergeFrom
    -1.02
     Pfar
    -1.00
    (
    -1.00
    ֪
    -1.00
     his
    -0.99
     Reised
    -0.98
     kathol
    -0.98
    èdent
    -0.98
    روابط
    -0.96
    ᆺ
    -0.96
    POSITIVE LOGITS
     you
    1.22
     to
    1.15
    ⟺
    1.08
     أثناء
    1.06
     spesifik
    1.04
     خریدار
    1.04
     aggiun
    1.02
     idag
    1.02
     DÍA
    1.02
     против
    0.96
    Activations Density 0.065%

    No Known Activations