© 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. 22-GEMMASCOPE-RES-131K
    7. 66059
    Prev
    Next
    INDEX
    Explanations

    cities and regions

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

    The neuron flags numeric tokens—especially multi-digit numbers (including decimals)—that typically represent data values, counts, or statistics in the text.

    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
     dimensione
    -1.08
    美味しく
    -1.06
     creer
    -1.05
     sanitaria
    -1.05
     nationwide
    -1.04
     nacionales
    -1.02
     durata
    -1.01
     nationaux
    -0.97
    kod
    -0.96
     soste
    -0.95
    POSITIVE LOGITS
     and
    1.97
     area
    1.44
     region
    1.16
     oraz
    1.05
    LOCAL
    1.05
     மற்றும்
    1.02
     or
    1.02
     locality
    0.98
     sederhana
    0.98
     okolí
    0.96
    Activations Density 0.075%

    No Known Activations