© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 92894
    Prev
    Next
    INDEX
    Explanations

    product inhibition

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

    coordinates or numerical positions in technical diagrams and code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on numeric tokens—especially standalone numbers and numeric data values (including coordinates or measurements).

    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
     dirigió
    -1.09
     błę
    -1.06
     hins
    -1.05
     kirj
    -1.03
     kupić
    -1.03
     mídia
    -1.02
     wybrać
    -1.01
     schnee
    -1.01
     mój
    -1.00
     medlemmer
    -1.00
    POSITIVE LOGITS
     ткани
    1.10
    辙
    1.04
    ὴν
    0.94
     fanns
    0.89
     impri
    0.89
    Pom
    0.89
     figuras
    0.88
     inertial
    0.88
    ftagPool
    0.88
     Mitteln
    0.88
    Activations Density 0.001%

    No Known Activations